docs/mcp.md

Example Clients

Source: https://modelcontextprotocol.io/clients

A list of applications that support MCP integrations

This page provides an overview of applications that support the Model Context Protocol (MCP). Each client may support different MCP features, allowing for varying levels of integration with MCP servers.

Feature support matrix

Client	Resources	Prompts	Tools	Sampling	Roots	Notes
Claude Desktop App	✅	✅	✅	❌	❌	Full support for all MCP features
5ire	❌	❌	✅	❌	❌	Supports tools.
BeeAI Framework	❌	❌	✅	❌	❌	Supports tools in agentic workflows.
Cline	✅	❌	✅	❌	❌	Supports tools and resources.
Continue	✅	✅	✅	❌	❌	Full support for all MCP features
Cursor	❌	❌	✅	❌	❌	Supports tools.
Emacs Mcp	❌	❌	✅	❌	❌	Supports tools in Emacs.
Firebase Genkit	⚠️	✅	✅	❌	❌	Supports resource list and lookup through tools.
GenAIScript	❌	❌	✅	❌	❌	Supports tools.
Goose	❌	❌	✅	❌	❌	Supports tools.
LibreChat	❌	❌	✅	❌	❌	Supports tools for Agents
mcp-agent	❌	❌	✅	⚠️	❌	Supports tools, server connection management, and agent workflows.
oterm	❌	❌	✅	❌	❌	Supports tools.
Roo Code	✅	❌	✅	❌	❌	Supports tools and resources.
Sourcegraph Cody	✅	❌	❌	❌	❌	Supports resources through OpenCTX
Superinterface	❌	❌	✅	❌	❌	Supports tools
TheiaAI/TheiaIDE	❌	❌	✅	❌	❌	Supports tools for Agents in Theia AI and the AI-powered Theia IDE
Windsurf Editor	❌	❌	✅	❌	❌	Supports tools with AI Flow for collaborative development.
Zed	❌	✅	❌	❌	❌	Prompts appear as slash commands
SpinAI	❌	❌	✅	❌	❌	Supports tools for Typescript AI Agents
OpenSumi	❌	❌	✅	❌	❌	Supports tools in OpenSumi
Daydreams Agents	✅	✅	✅	❌	❌	Support for drop in Servers to Daydreams agents

Client details

Claude Desktop App

The Claude desktop application provides comprehensive support for MCP, enabling deep integration with local tools and data sources.

Key features:

• Full support for resources, allowing attachment of local files and data
• Support for prompt templates
• Tool integration for executing commands and scripts
• Local server connections for enhanced privacy and security

ⓘ Note: The Claude.ai web application does not currently support MCP. MCP features are only available in the desktop application.

5ire

5ire is an open source cross-platform desktop AI assistant that supports tools through MCP servers.

Key features:

• Built-in MCP servers can be quickly enabled and disabled.
• Users can add more servers by modifying the configuration file.
• It is open-source and user-friendly, suitable for beginners.
• Future support for MCP will be continuously improved.

BeeAI Framework

BeeAI Framework is an open-source framework for building, deploying, and serving powerful agentic workflows at scale. The framework includes the MCP Tool, a native feature that simplifies the integration of MCP servers into agentic workflows.

Key features:

• Seamlessly incorporate MCP tools into agentic workflows.
• Quickly instantiate framework-native tools from connected MCP client(s).
• Planned future support for agentic MCP capabilities.

Learn more:

• Example of using MCP tools in agentic workflow

Cline

Cline is an autonomous coding agent in VS Code that edits files, runs commands, uses a browser, and more–with your permission at each step.

Key features:

• Create and add tools through natural language (e.g. "add a tool that searches the web")
• Share custom MCP servers Cline creates with others via the ~/Documents/Cline/MCP directory
• Displays configured MCP servers along with their tools, resources, and any error logs

Continue

Continue is an open-source AI code assistant, with built-in support for all MCP features.

Key features

• Type "@" to mention MCP resources
• Prompt templates surface as slash commands
• Use both built-in and MCP tools directly in chat
• Supports VS Code and JetBrains IDEs, with any LLM

Cursor

Cursor is an AI code editor.

Key Features:

• Support for MCP tools in Cursor Composer
• Support for both STDIO and SSE

Emacs Mcp

Emacs Mcp is an Emacs client designed to interface with MCP servers, enabling seamless connections and interactions. It provides MCP tool invocation support for AI plugins like gptel and llm, adhering to Emacs' standard tool invocation format. This integration enhances the functionality of AI tools within the Emacs ecosystem.

Key features:

• Provides MCP tool support for Emacs.

Firebase Genkit

Genkit is Firebase's SDK for building and integrating GenAI features into applications. The genkitx-mcp plugin enables consuming MCP servers as a client or creating MCP servers from Genkit tools and prompts.

Key features:

• Client support for tools and prompts (resources partially supported)
• Rich discovery with support in Genkit's Dev UI playground
• Seamless interoperability with Genkit's existing tools and prompts
• Works across a wide variety of GenAI models from top providers

GenAIScript

Programmatically assemble prompts for LLMs using GenAIScript (in JavaScript). Orchestrate LLMs, tools, and data in JavaScript.

Key features:

• JavaScript toolbox to work with prompts
• Abstraction to make it easy and productive
• Seamless Visual Studio Code integration

Goose

Goose is an open source AI agent that supercharges your software development by automating coding tasks.

Key features:

• Expose MCP functionality to Goose through tools.
• MCPs can be installed directly via the extensions directory, CLI, or UI.
• Goose allows you to extend its functionality by building your own MCP servers.
• Includes built-in tools for development, web scraping, automation, memory, and integrations with JetBrains and Google Drive.

LibreChat

LibreChat is an open-source, customizable AI chat UI that supports multiple AI providers, now including MCP integration.

Key features:

• Extend current tool ecosystem, including Code Interpreter and Image generation tools, through MCP servers
• Add tools to customizable Agents, using a variety of LLMs from top providers
• Open-source and self-hostable, with secure multi-user support
• Future roadmap includes expanded MCP feature support

mcp-agent

mcp-agent is a simple, composable framework to build agents using Model Context Protocol.

Key features:

• Automatic connection management of MCP servers.
• Expose tools from multiple servers to an LLM.
• Implements every pattern defined in Building Effective Agents.
• Supports workflow pause/resume signals, such as waiting for human feedback.

oterm

oterm is a terminal client for Ollama allowing users to create chats/agents.

Key features:

• Support for multiple fully customizable chat sessions with Ollama connected with tools.
• Support for MCP tools.

Roo Code

Roo Code enables AI coding assistance via MCP.

Key features:

• Support for MCP tools and resources
• Integration with development workflows
• Extensible AI capabilities

Sourcegraph Cody

Cody is Sourcegraph's AI coding assistant, which implements MCP through OpenCTX.

Key features:

• Support for MCP resources
• Integration with Sourcegraph's code intelligence
• Uses OpenCTX as an abstraction layer
• Future support planned for additional MCP features

SpinAI

SpinAI is an open-source TypeScript framework for building observable AI agents. The framework provides native MCP compatibility, allowing agents to seamlessly integrate with MCP servers and tools.

Key features:

• Built-in MCP compatibility for AI agents
• Open-source TypeScript framework
• Observable agent architecture
• Native support for MCP tools integration

Superinterface

Superinterface is AI infrastructure and a developer platform to build in-app AI assistants with support for MCP, interactive components, client-side function calling and more.

Key features:

• Use tools from MCP servers in assistants embedded via React components or script tags
• SSE transport support
• Use any AI model from any AI provider (OpenAI, Anthropic, Ollama, others)

TheiaAI/TheiaIDE

Theia AI is a framework for building AI-enhanced tools and IDEs. The AI-powered Theia IDE is an open and flexible development environment built on Theia AI.

Key features:

• Tool Integration: Theia AI enables AI agents, including those in the Theia IDE, to utilize MCP servers for seamless tool interaction.
• Customizable Prompts: The Theia IDE allows users to define and adapt prompts, dynamically integrating MCP servers for tailored workflows.
• Custom agents: The Theia IDE supports creating custom agents that leverage MCP capabilities, enabling users to design dedicated workflows on the fly.

Theia AI and Theia IDE's MCP integration provide users with flexibility, making them powerful platforms for exploring and adapting MCP.

Learn more:

• Theia IDE and Theia AI MCP Announcement
• Download the AI-powered Theia IDE

Windsurf Editor

Windsurf Editor is an agentic IDE that combines AI assistance with developer workflows. It features an innovative AI Flow system that enables both collaborative and independent AI interactions while maintaining developer control.

Key features:

• Revolutionary AI Flow paradigm for human-AI collaboration
• Intelligent code generation and understanding
• Rich development tools with multi-model support

Zed

Zed is a high-performance code editor with built-in MCP support, focusing on prompt templates and tool integration.

Key features:

• Prompt templates surface as slash commands in the editor
• Tool integration for enhanced coding workflows
• Tight integration with editor features and workspace context
• Does not support MCP resources

OpenSumi

OpenSumi is a framework helps you quickly build AI Native IDE products.

Key features:

• Supports MCP tools in OpenSumi
• Supports built-in IDE MCP servers and custom MCP servers

Daydreams

Daydreams is a generative agent framework for executing anything onchain

Key features:

• Supports MCP Servers in config
• Exposes MCP Client

Adding MCP support to your application

If you've added MCP support to your application, we encourage you to submit a pull request to add it to this list. MCP integration can provide your users with powerful contextual AI capabilities and make your application part of the growing MCP ecosystem.

Benefits of adding MCP support:

• Enable users to bring their own context and tools
• Join a growing ecosystem of interoperable AI applications
• Provide users with flexible integration options
• Support local-first AI workflows

To get started with implementing MCP in your application, check out our Python or TypeScript SDK Documentation

Updates and corrections

This list is maintained by the community. If you notice any inaccuracies or would like to update information about MCP support in your application, please submit a pull request or open an issue in our documentation repository.

Contributing

Source: https://modelcontextprotocol.io/development/contributing

How to participate in Model Context Protocol development

We welcome contributions from the community! Please review our contributing guidelines for details on how to submit changes.

All contributors must adhere to our Code of Conduct.

For questions and discussions, please use GitHub Discussions.

Roadmap

Source: https://modelcontextprotocol.io/development/roadmap

Our plans for evolving Model Context Protocol (H1 2025)

The Model Context Protocol is rapidly evolving. This page outlines our current thinking on key priorities and future direction for the first half of 2025, though these may change significantly as the project develops.

The ideas presented here are not commitments—we may solve these challenges differently than described, or some may not materialize at all. This is also not an exhaustive list; we may incorporate work that isn't mentioned here.

We encourage community participation! Each section links to relevant discussions where you can learn more and contribute your thoughts.

Remote MCP Support

Our top priority is improving remote MCP connections, allowing clients to securely connect to MCP servers over the internet. Key initiatives include:

• Authentication & Authorization: Adding standardized auth capabilities, particularly focused on OAuth 2.0 support.

• Service Discovery: Defining how clients can discover and connect to remote MCP servers.

• Stateless Operations: Thinking about whether MCP could encompass serverless environments too, where they will need to be mostly stateless.

Reference Implementations

To help developers build with MCP, we want to offer documentation for:

• Client Examples: Comprehensive reference client implementation(s), demonstrating all protocol features
• Protocol Drafting: Streamlined process for proposing and incorporating new protocol features

Distribution & Discovery

Looking ahead, we're exploring ways to make MCP servers more accessible. Some areas we may investigate include:

• Package Management: Standardized packaging format for MCP servers
• Installation Tools: Simplified server installation across MCP clients
• Sandboxing: Improved security through server isolation
• Server Registry: A common directory for discovering available MCP servers

Agent Support

We're expanding MCP's capabilities for complex agentic workflows, particularly focusing on:

• Hierarchical Agent Systems: Improved support for trees of agents through namespacing and topology awareness.

• Interactive Workflows: Better handling of user permissions and information requests across agent hierarchies, and ways to send output to users instead of models.

• Streaming Results: Real-time updates from long-running agent operations.

Broader Ecosystem

We're also invested in:

• Community-Led Standards Development: Fostering a collaborative ecosystem where all AI providers can help shape MCP as an open standard through equal participation and shared governance, ensuring it meets the needs of diverse AI applications and use cases.
• Additional Modalities: Expanding beyond text to support audio, video, and other formats.
• [Standardization] Considering standardization through a standardization body.

Get Involved

We welcome community participation in shaping MCP's future. Visit our GitHub Discussions to join the conversation and contribute your ideas.

What's New

Source: https://modelcontextprotocol.io/development/updates

The latest updates and improvements to MCP

* We're excited to announce that the Java SDK developed by Spring AI at VMware Tanzu is now the official [Java SDK](https://github.com/modelcontextprotocol/java-sdk) for MCP. This joins our existing Kotlin SDK in our growing list of supported languages. The Spring AI team will maintain the SDK as an integral part of the Model Context Protocol organization. We're thrilled to welcome them to the MCP community! * Version [1.2.1](https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.2.1) of the MCP Python SDK has been released, delivering important stability improvements and bug fixes. * Simplified, express-like API in the [TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk) * Added 8 new clients to the [clients page](https://modelcontextprotocol.io/clients) * FastMCP API in the [Python SDK](https://github.com/modelcontextprotocol/python-sdk) * Dockerized MCP servers in the [servers repo](https://github.com/modelcontextprotocol/servers) * Jetbrains released a Kotlin SDK for MCP! * For a sample MCP Kotlin server, check out [this repository](https://github.com/modelcontextprotocol/kotlin-sdk/tree/main/samples/kotlin-mcp-server)

Core architecture

Source: https://modelcontextprotocol.io/docs/concepts/architecture

Understand how MCP connects clients, servers, and LLMs

The Model Context Protocol (MCP) is built on a flexible, extensible architecture that enables seamless communication between LLM applications and integrations. This document covers the core architectural components and concepts.

Overview

MCP follows a client-server architecture where:

• Hosts are LLM applications (like Claude Desktop or IDEs) that initiate connections
• Clients maintain 1:1 connections with servers, inside the host application
• Servers provide context, tools, and prompts to clients

flowchart LR
    subgraph "Host"
        client1[MCP Client]
        client2[MCP Client]
    end
    subgraph "Server Process"
        server1[MCP Server]
    end
    subgraph "Server Process"
        server2[MCP Server]
    end

    client1 <-->|Transport Layer| server1
    client2 <-->|Transport Layer| server2

Core components

Protocol layer

The protocol layer handles message framing, request/response linking, and high-level communication patterns.

```typescript class Protocol { // Handle incoming requests setRequestHandler(schema: T, handler: (request: T, extra: RequestHandlerExtra) => Promise): void

    // Handle incoming notifications
    setNotificationHandler<T>(schema: T, handler: (notification: T) => Promise<void>): void

    // Send requests and await responses
    request<T>(request: Request, schema: T, options?: RequestOptions): Promise<T>

    // Send one-way notifications
    notification(notification: Notification): Promise<void>
}
```

```python class Session(BaseSession[RequestT, NotificationT, ResultT]): async def send_request( self, request: RequestT, result_type: type[Result] ) -> Result: """ Send request and wait for response. Raises McpError if response contains error. """ # Request handling implementation

    async def send_notification(
        self,
        notification: NotificationT
    ) -> None:
        """Send one-way notification that doesn't expect response."""
        # Notification handling implementation

    async def _received_request(
        self,
        responder: RequestResponder[ReceiveRequestT, ResultT]
    ) -> None:
        """Handle incoming request from other side."""
        # Request handling implementation

    async def _received_notification(
        self,
        notification: ReceiveNotificationT
    ) -> None:
        """Handle incoming notification from other side."""
        # Notification handling implementation
```

Key classes include:

• Protocol
• Client
• Server

Transport layer

The transport layer handles the actual communication between clients and servers. MCP supports multiple transport mechanisms:

1. Stdio transport

   • Uses standard input/output for communication
   • Ideal for local processes

2. HTTP with SSE transport

   • Uses Server-Sent Events for server-to-client messages
   • HTTP POST for client-to-server messages

All transports use JSON-RPC 2.0 to exchange messages. See the specification for detailed information about the Model Context Protocol message format.

Message types

MCP has these main types of messages:

1. Requests expect a response from the other side:

   interface Request {
     method: string;
     params?: { ... };
   }
   

2. Results are successful responses to requests:

   interface Result {
     [key: string]: unknown;
   }
   

3. Errors indicate that a request failed:

   interface Error {
     code: number;
     message: string;
     data?: unknown;
   }
   

4. Notifications are one-way messages that don't expect a response:

   interface Notification {
     method: string;
     params?: { ... };
   }
   

Connection lifecycle

1. Initialization

sequenceDiagram
    participant Client
    participant Server

    Client->>Server: initialize request
    Server->>Client: initialize response
    Client->>Server: initialized notification

    Note over Client,Server: Connection ready for use

1. Client sends initialize request with protocol version and capabilities
2. Server responds with its protocol version and capabilities
3. Client sends initialized notification as acknowledgment
4. Normal message exchange begins

2. Message exchange

After initialization, the following patterns are supported:

• Request-Response: Client or server sends requests, the other responds
• Notifications: Either party sends one-way messages

3. Termination

Either party can terminate the connection:

• Clean shutdown via close()
• Transport disconnection
• Error conditions

Error handling

MCP defines these standard error codes:

enum ErrorCode {
  // Standard JSON-RPC error codes
  ParseError = -32700,
  InvalidRequest = -32600,
  MethodNotFound = -32601,
  InvalidParams = -32602,
  InternalError = -32603
}

SDKs and applications can define their own error codes above -32000.

Errors are propagated through:

• Error responses to requests
• Error events on transports
• Protocol-level error handlers

Implementation example

Here's a basic example of implementing an MCP server:

```typescript import { Server } from "@modelcontextprotocol/sdk/server/index.js"; import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new Server({
  name: "example-server",
  version: "1.0.0"
}, {
  capabilities: {
    resources: {}
  }
});

// Handle requests
server.setRequestHandler(ListResourcesRequestSchema, async () => {
  return {
    resources: [
      {
        uri: "example://resource",
        name: "Example Resource"
      }
    ]
  };
});

// Connect transport
const transport = new StdioServerTransport();
await server.connect(transport);
```

```python import asyncio import mcp.types as types from mcp.server import Server from mcp.server.stdio import stdio_server

app = Server("example-server")

@app.list_resources()
async def list_resources() -> list[types.Resource]:
    return [
        types.Resource(
            uri="example://resource",
            name="Example Resource"
        )
    ]

async def main():
    async with stdio_server() as streams:
        await app.run(
            streams[0],
            streams[1],
            app.create_initialization_options()
        )

if __name__ == "__main__":
    asyncio.run(main)
```

Best practices

Transport selection

1. Local communication

   • Use stdio transport for local processes
   • Efficient for same-machine communication
   • Simple process management

2. Remote communication

   • Use SSE for scenarios requiring HTTP compatibility
   • Consider security implications including authentication and authorization

Message handling

1. Request processing

   • Validate inputs thoroughly
   • Use type-safe schemas
   • Handle errors gracefully
   • Implement timeouts

2. Progress reporting

   • Use progress tokens for long operations
   • Report progress incrementally
   • Include total progress when known

3. Error management

   • Use appropriate error codes
   • Include helpful error messages
   • Clean up resources on errors

Security considerations

1. Transport security

   • Use TLS for remote connections
   • Validate connection origins
   • Implement authentication when needed

2. Message validation

   • Validate all incoming messages
   • Sanitize inputs
   • Check message size limits
   • Verify JSON-RPC format

3. Resource protection

   • Implement access controls
   • Validate resource paths
   • Monitor resource usage
   • Rate limit requests

4. Error handling

   • Don't leak sensitive information
   • Log security-relevant errors
   • Implement proper cleanup
   • Handle DoS scenarios

Debugging and monitoring

1. Logging

   • Log protocol events
   • Track message flow
   • Monitor performance
   • Record errors

2. Diagnostics

   • Implement health checks
   • Monitor connection state
   • Track resource usage
   • Profile performance

3. Testing

   • Test different transports
   • Verify error handling
   • Check edge cases
   • Load test servers

Prompts

Source: https://modelcontextprotocol.io/docs/concepts/prompts

Create reusable prompt templates and workflows

Prompts enable servers to define reusable prompt templates and workflows that clients can easily surface to users and LLMs. They provide a powerful way to standardize and share common LLM interactions.

Prompts are designed to be **user-controlled**, meaning they are exposed from servers to clients with the intention of the user being able to explicitly select them for use.

Overview

Prompts in MCP are predefined templates that can:

• Accept dynamic arguments
• Include context from resources
• Chain multiple interactions
• Guide specific workflows
• Surface as UI elements (like slash commands)

Prompt structure

Each prompt is defined with:

{
  name: string;              // Unique identifier for the prompt
  description?: string;      // Human-readable description
  arguments?: [              // Optional list of arguments
    {
      name: string;          // Argument identifier
      description?: string;  // Argument description
      required?: boolean;    // Whether argument is required
    }
  ]
}

Discovering prompts

Clients can discover available prompts through the prompts/list endpoint:

// Request
{
  method: "prompts/list"
}

// Response
{
  prompts: [
    {
      name: "analyze-code",
      description: "Analyze code for potential improvements",
      arguments: [
        {
          name: "language",
          description: "Programming language",
          required: true
        }
      ]
    }
  ]
}

Using prompts

To use a prompt, clients make a prompts/get request:

// Request
{
  method: "prompts/get",
  params: {
    name: "analyze-code",
    arguments: {
      language: "python"
    }
  }
}

// Response
{
  description: "Analyze Python code for potential improvements",
  messages: [
    {
      role: "user",
      content: {
        type: "text",
        text: "Please analyze the following Python code for potential improvements:\n\n```python\ndef calculate_sum(numbers):\n    total = 0\n    for num in numbers:\n        total = total + num\n    return total\n\nresult = calculate_sum([1, 2, 3, 4, 5])\nprint(result)\n```"
      }
    }
  ]
}

Dynamic prompts

Prompts can be dynamic and include:

Embedded resource context

{
  "name": "analyze-project",
  "description": "Analyze project logs and code",
  "arguments": [
    {
      "name": "timeframe",
      "description": "Time period to analyze logs",
      "required": true
    },
    {
      "name": "fileUri",
      "description": "URI of code file to review",
      "required": true
    }
  ]
}

When handling the prompts/get request:

{
  "messages": [
    {
      "role": "user",
      "content": {
        "type": "text",
        "text": "Analyze these system logs and the code file for any issues:"
      }
    },
    {
      "role": "user",
      "content": {
        "type": "resource",
        "resource": {
          "uri": "logs://recent?timeframe=1h",
          "text": "[2024-03-14 15:32:11] ERROR: Connection timeout in network.py:127\n[2024-03-14 15:32:15] WARN: Retrying connection (attempt 2/3)\n[2024-03-14 15:32:20] ERROR: Max retries exceeded",
          "mimeType": "text/plain"
        }
      }
    },
    {
      "role": "user",
      "content": {
        "type": "resource",
        "resource": {
          "uri": "file:///path/to/code.py",
          "text": "def connect_to_service(timeout=30):\n    retries = 3\n    for attempt in range(retries):\n        try:\n            return establish_connection(timeout)\n        except TimeoutError:\n            if attempt == retries - 1:\n                raise\n            time.sleep(5)\n\ndef establish_connection(timeout):\n    # Connection implementation\n    pass",
          "mimeType": "text/x-python"
        }
      }
    }
  ]
}

Multi-step workflows

const debugWorkflow = {
  name: "debug-error",
  async getMessages(error: string) {
    return [
      {
        role: "user",
        content: {
          type: "text",
          text: `Here's an error I'm seeing: ${error}`
        }
      },
      {
        role: "assistant",
        content: {
          type: "text",
          text: "I'll help analyze this error. What have you tried so far?"
        }
      },
      {
        role: "user",
        content: {
          type: "text",
          text: "I've tried restarting the service, but the error persists."
        }
      }
    ];
  }
};

Example implementation

Here's a complete example of implementing prompts in an MCP server:

```typescript import { Server } from "@modelcontextprotocol/sdk/server"; import { ListPromptsRequestSchema, GetPromptRequestSchema } from "@modelcontextprotocol/sdk/types";

const PROMPTS = {
  "git-commit": {
    name: "git-commit",
    description: "Generate a Git commit message",
    arguments: [
      {
        name: "changes",
        description: "Git diff or description of changes",
        required: true
      }
    ]
  },
  "explain-code": {
    name: "explain-code",
    description: "Explain how code works",
    arguments: [
      {
        name: "code",
        description: "Code to explain",
        required: true
      },
      {
        name: "language",
        description: "Programming language",
        required: false
      }
    ]
  }
};

const server = new Server({
  name: "example-prompts-server",
  version: "1.0.0"
}, {
  capabilities: {
    prompts: {}
  }
});

// List available prompts
server.setRequestHandler(ListPromptsRequestSchema, async () => {
  return {
    prompts: Object.values(PROMPTS)
  };
});

// Get specific prompt
server.setRequestHandler(GetPromptRequestSchema, async (request) => {
  const prompt = PROMPTS[request.params.name];
  if (!prompt) {
    throw new Error(`Prompt not found: ${request.params.name}`);
  }

  if (request.params.name === "git-commit") {
    return {
      messages: [
        {
          role: "user",
          content: {
            type: "text",
            text: `Generate a concise but descriptive commit message for these changes:\n\n${request.params.arguments?.changes}`
          }
        }
      ]
    };
  }

  if (request.params.name === "explain-code") {
    const language = request.params.arguments?.language || "Unknown";
    return {
      messages: [
        {
          role: "user",
          content: {
            type: "text",
            text: `Explain how this ${language} code works:\n\n${request.params.arguments?.code}`
          }
        }
      ]
    };
  }

  throw new Error("Prompt implementation not found");
});
```

```python from mcp.server import Server import mcp.types as types

# Define available prompts
PROMPTS = {
    "git-commit": types.Prompt(
        name="git-commit",
        description="Generate a Git commit message",
        arguments=[
            types.PromptArgument(
                name="changes",
                description="Git diff or description of changes",
                required=True
            )
        ],
    ),
    "explain-code": types.Prompt(
        name="explain-code",
        description="Explain how code works",
        arguments=[
            types.PromptArgument(
                name="code",
                description="Code to explain",
                required=True
            ),
            types.PromptArgument(
                name="language",
                description="Programming language",
                required=False
            )
        ],
    )
}

# Initialize server
app = Server("example-prompts-server")

@app.list_prompts()
async def list_prompts() -> list[types.Prompt]:
    return list(PROMPTS.values())

@app.get_prompt()
async def get_prompt(
    name: str, arguments: dict[str, str] | None = None
) -> types.GetPromptResult:
    if name not in PROMPTS:
        raise ValueError(f"Prompt not found: {name}")

    if name == "git-commit":
        changes = arguments.get("changes") if arguments else ""
        return types.GetPromptResult(
            messages=[
                types.PromptMessage(
                    role="user",
                    content=types.TextContent(
                        type="text",
                        text=f"Generate a concise but descriptive commit message "
                        f"for these changes:\n\n{changes}"
                    )
                )
            ]
        )

    if name == "explain-code":
        code = arguments.get("code") if arguments else ""
        language = arguments.get("language", "Unknown") if arguments else "Unknown"
        return types.GetPromptResult(
            messages=[
                types.PromptMessage(
                    role="user",
                    content=types.TextContent(
                        type="text",
                        text=f"Explain how this {language} code works:\n\n{code}"
                    )
                )
            ]
        )

    raise ValueError("Prompt implementation not found")
```

Best practices

When implementing prompts:

1. Use clear, descriptive prompt names
2. Provide detailed descriptions for prompts and arguments
3. Validate all required arguments
4. Handle missing arguments gracefully
5. Consider versioning for prompt templates
6. Cache dynamic content when appropriate
7. Implement error handling
8. Document expected argument formats
9. Consider prompt composability
10. Test prompts with various inputs

UI integration

Prompts can be surfaced in client UIs as:

• Slash commands
• Quick actions
• Context menu items
• Command palette entries
• Guided workflows
• Interactive forms

Updates and changes

Servers can notify clients about prompt changes:

1. Server capability: prompts.listChanged
2. Notification: notifications/prompts/list_changed
3. Client re-fetches prompt list

Security considerations

When implementing prompts:

• Validate all arguments
• Sanitize user input
• Consider rate limiting
• Implement access controls
• Audit prompt usage
• Handle sensitive data appropriately
• Validate generated content
• Implement timeouts
• Consider prompt injection risks
• Document security requirements

Resources

Source: https://modelcontextprotocol.io/docs/concepts/resources

Expose data and content from your servers to LLMs

Resources are a core primitive in the Model Context Protocol (MCP) that allow servers to expose data and content that can be read by clients and used as context for LLM interactions.

Resources are designed to be **application-controlled**, meaning that the client application can decide how and when they should be used. Different MCP clients may handle resources differently. For example:

• Claude Desktop currently requires users to explicitly select resources before they can be used
• Other clients might automatically select resources based on heuristics
• Some implementations may even allow the AI model itself to determine which resources to use

Server authors should be prepared to handle any of these interaction patterns when implementing resource support. In order to expose data to models automatically, server authors should use a model-controlled primitive such as Tools.

Overview

Resources represent any kind of data that an MCP server wants to make available to clients. This can include:

• File contents
• Database records
• API responses
• Live system data
• Screenshots and images
• Log files
• And more

Each resource is identified by a unique URI and can contain either text or binary data.

Resource URIs

Resources are identified using URIs that follow this format:

[protocol]://[host]/[path]

For example:

• file:///home/user/documents/report.pdf
• postgres://database/customers/schema
• screen://localhost/display1

The protocol and path structure is defined by the MCP server implementation. Servers can define their own custom URI schemes.

Resource types

Resources can contain two types of content:

Text resources

Text resources contain UTF-8 encoded text data. These are suitable for:

• Source code
• Configuration files
• Log files
• JSON/XML data
• Plain text

Binary resources

Binary resources contain raw binary data encoded in base64. These are suitable for:

• Images
• PDFs
• Audio files
• Video files
• Other non-text formats

Resource discovery

Clients can discover available resources through two main methods:

Direct resources

Servers expose a list of concrete resources via the resources/list endpoint. Each resource includes:

{
  uri: string;           // Unique identifier for the resource
  name: string;          // Human-readable name
  description?: string;  // Optional description
  mimeType?: string;     // Optional MIME type
}

Resource templates

For dynamic resources, servers can expose URI templates that clients can use to construct valid resource URIs:

{
  uriTemplate: string;   // URI template following RFC 6570
  name: string;          // Human-readable name for this type
  description?: string;  // Optional description
  mimeType?: string;     // Optional MIME type for all matching resources
}

Reading resources

To read a resource, clients make a resources/read request with the resource URI.

The server responds with a list of resource contents:

{
  contents: [
    {
      uri: string;        // The URI of the resource
      mimeType?: string;  // Optional MIME type

      // One of:
      text?: string;      // For text resources
      blob?: string;      // For binary resources (base64 encoded)
    }
  ]
}

Servers may return multiple resources in response to one `resources/read` request. This could be used, for example, to return a list of files inside a directory when the directory is read.

Resource updates

MCP supports real-time updates for resources through two mechanisms:

List changes

Servers can notify clients when their list of available resources changes via the notifications/resources/list_changed notification.

Content changes

Clients can subscribe to updates for specific resources:

1. Client sends resources/subscribe with resource URI
2. Server sends notifications/resources/updated when the resource changes
3. Client can fetch latest content with resources/read
4. Client can unsubscribe with resources/unsubscribe

Example implementation

Here's a simple example of implementing resource support in an MCP server:

```typescript const server = new Server({ name: "example-server", version: "1.0.0" }, { capabilities: { resources: {} } });

// List available resources
server.setRequestHandler(ListResourcesRequestSchema, async () => {
  return {
    resources: [
      {
        uri: "file:///logs/app.log",
        name: "Application Logs",
        mimeType: "text/plain"
      }
    ]
  };
});

// Read resource contents
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
  const uri = request.params.uri;

  if (uri === "file:///logs/app.log") {
    const logContents = await readLogFile();
    return {
      contents: [
        {
          uri,
          mimeType: "text/plain",
          text: logContents
        }
      ]
    };
  }

  throw new Error("Resource not found");
});
```

```python app = Server("example-server")

@app.list_resources()
async def list_resources() -> list[types.Resource]:
    return [
        types.Resource(
            uri="file:///logs/app.log",
            name="Application Logs",
            mimeType="text/plain"
        )
    ]

@app.read_resource()
async def read_resource(uri: AnyUrl) -> str:
    if str(uri) == "file:///logs/app.log":
        log_contents = await read_log_file()
        return log_contents

    raise ValueError("Resource not found")

# Start server
async with stdio_server() as streams:
    await app.run(
        streams[0],
        streams[1],
        app.create_initialization_options()
    )
```

Best practices

When implementing resource support:

1. Use clear, descriptive resource names and URIs
2. Include helpful descriptions to guide LLM understanding
3. Set appropriate MIME types when known
4. Implement resource templates for dynamic content
5. Use subscriptions for frequently changing resources
6. Handle errors gracefully with clear error messages
7. Consider pagination for large resource lists
8. Cache resource contents when appropriate
9. Validate URIs before processing
10. Document your custom URI schemes

Security considerations

When exposing resources:

• Validate all resource URIs
• Implement appropriate access controls
• Sanitize file paths to prevent directory traversal
• Be cautious with binary data handling
• Consider rate limiting for resource reads
• Audit resource access
• Encrypt sensitive data in transit
• Validate MIME types
• Implement timeouts for long-running reads
• Handle resource cleanup appropriately

Roots

Source: https://modelcontextprotocol.io/docs/concepts/roots

Understanding roots in MCP

Roots are a concept in MCP that define the boundaries where servers can operate. They provide a way for clients to inform servers about relevant resources and their locations.

What are Roots?

A root is a URI that a client suggests a server should focus on. When a client connects to a server, it declares which roots the server should work with. While primarily used for filesystem paths, roots can be any valid URI including HTTP URLs.

For example, roots could be:

file:///home/user/projects/myapp
https://api.example.com/v1

Why Use Roots?

Roots serve several important purposes:

1. Guidance: They inform servers about relevant resources and locations
2. Clarity: Roots make it clear which resources are part of your workspace
3. Organization: Multiple roots let you work with different resources simultaneously

How Roots Work

When a client supports roots, it:

1. Declares the roots capability during connection
2. Provides a list of suggested roots to the server
3. Notifies the server when roots change (if supported)

While roots are informational and not strictly enforcing, servers should:

1. Respect the provided roots
2. Use root URIs to locate and access resources
3. Prioritize operations within root boundaries

Common Use Cases

Roots are commonly used to define:

• Project directories
• Repository locations
• API endpoints
• Configuration locations
• Resource boundaries

Best Practices

When working with roots:

1. Only suggest necessary resources
2. Use clear, descriptive names for roots
3. Monitor root accessibility
4. Handle root changes gracefully

Example

Here's how a typical MCP client might expose roots:

{
  "roots": [
    {
      "uri": "file:///home/user/projects/frontend",
      "name": "Frontend Repository"
    },
    {
      "uri": "https://api.example.com/v1",
      "name": "API Endpoint"
    }
  ]
}

This configuration suggests the server focus on both a local repository and an API endpoint while keeping them logically separated.

Sampling

Source: https://modelcontextprotocol.io/docs/concepts/sampling

Let your servers request completions from LLMs

Sampling is a powerful MCP feature that allows servers to request LLM completions through the client, enabling sophisticated agentic behaviors while maintaining security and privacy.

This feature of MCP is not yet supported in the Claude Desktop client.

How sampling works

The sampling flow follows these steps:

1. Server sends a sampling/createMessage request to the client
2. Client reviews the request and can modify it
3. Client samples from an LLM
4. Client reviews the completion
5. Client returns the result to the server

This human-in-the-loop design ensures users maintain control over what the LLM sees and generates.

Message format

Sampling requests use a standardized message format:

{
  messages: [
    {
      role: "user" | "assistant",
      content: {
        type: "text" | "image",

        // For text:
        text?: string,

        // For images:
        data?: string,             // base64 encoded
        mimeType?: string
      }
    }
  ],
  modelPreferences?: {
    hints?: [{
      name?: string                // Suggested model name/family
    }],
    costPriority?: number,         // 0-1, importance of minimizing cost
    speedPriority?: number,        // 0-1, importance of low latency
    intelligencePriority?: number  // 0-1, importance of capabilities
  },
  systemPrompt?: string,
  includeContext?: "none" | "thisServer" | "allServers",
  temperature?: number,
  maxTokens: number,
  stopSequences?: string[],
  metadata?: Record<string, unknown>
}

Request parameters

Messages

The messages array contains the conversation history to send to the LLM. Each message has:

• role: Either "user" or "assistant"
• content: The message content, which can be:
  • Text content with a text field
  • Image content with data (base64) and mimeType fields

Model preferences

The modelPreferences object allows servers to specify their model selection preferences:

• hints: Array of model name suggestions that clients can use to select an appropriate model:

  • name: String that can match full or partial model names (e.g. "claude-3", "sonnet")
  • Clients may map hints to equivalent models from different providers
  • Multiple hints are evaluated in preference order

• Priority values (0-1 normalized):

  • costPriority: Importance of minimizing costs
  • speedPriority: Importance of low latency response
  • intelligencePriority: Importance of advanced model capabilities

Clients make the final model selection based on these preferences and their available models.

System prompt

An optional systemPrompt field allows servers to request a specific system prompt. The client may modify or ignore this.

Context inclusion

The includeContext parameter specifies what MCP context to include:

• "none": No additional context
• "thisServer": Include context from the requesting server
• "allServers": Include context from all connected MCP servers

The client controls what context is actually included.

Sampling parameters

Fine-tune the LLM sampling with:

• temperature: Controls randomness (0.0 to 1.0)
• maxTokens: Maximum tokens to generate
• stopSequences: Array of sequences that stop generation
• metadata: Additional provider-specific parameters

Response format

The client returns a completion result:

{
  model: string,  // Name of the model used
  stopReason?: "endTurn" | "stopSequence" | "maxTokens" | string,
  role: "user" | "assistant",
  content: {
    type: "text" | "image",
    text?: string,
    data?: string,
    mimeType?: string
  }
}

Example request

Here's an example of requesting sampling from a client:

{
  "method": "sampling/createMessage",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": {
          "type": "text",
          "text": "What files are in the current directory?"
        }
      }
    ],
    "systemPrompt": "You are a helpful file system assistant.",
    "includeContext": "thisServer",
    "maxTokens": 100
  }
}

Best practices

When implementing sampling:

1. Always provide clear, well-structured prompts
2. Handle both text and image content appropriately
3. Set reasonable token limits
4. Include relevant context through includeContext
5. Validate responses before using them
6. Handle errors gracefully
7. Consider rate limiting sampling requests
8. Document expected sampling behavior
9. Test with various model parameters
10. Monitor sampling costs

Human in the loop controls

Sampling is designed with human oversight in mind:

For prompts

• Clients should show users the proposed prompt
• Users should be able to modify or reject prompts
• System prompts can be filtered or modified
• Context inclusion is controlled by the client

For completions

• Clients should show users the completion
• Users should be able to modify or reject completions
• Clients can filter or modify completions
• Users control which model is used

Security considerations

When implementing sampling:

• Validate all message content
• Sanitize sensitive information
• Implement appropriate rate limits
• Monitor sampling usage
• Encrypt data in transit
• Handle user data privacy
• Audit sampling requests
• Control cost exposure
• Implement timeouts
• Handle model errors gracefully

Common patterns

Agentic workflows

Sampling enables agentic patterns like:

• Reading and analyzing resources
• Making decisions based on context
• Generating structured data
• Handling multi-step tasks
• Providing interactive assistance

Context management

Best practices for context:

• Request minimal necessary context
• Structure context clearly
• Handle context size limits
• Update context as needed
• Clean up stale context

Error handling

Robust error handling should:

• Catch sampling failures
• Handle timeout errors
• Manage rate limits
• Validate responses
• Provide fallback behaviors
• Log errors appropriately

Limitations

Be aware of these limitations:

• Sampling depends on client capabilities
• Users control sampling behavior
• Context size has limits
• Rate limits may apply
• Costs should be considered
• Model availability varies
• Response times vary
• Not all content types supported

Tools

Source: https://modelcontextprotocol.io/docs/concepts/tools

Enable LLMs to perform actions through your server

Tools are a powerful primitive in the Model Context Protocol (MCP) that enable servers to expose executable functionality to clients. Through tools, LLMs can interact with external systems, perform computations, and take actions in the real world.

Tools are designed to be **model-controlled**, meaning that tools are exposed from servers to clients with the intention of the AI model being able to automatically invoke them (with a human in the loop to grant approval).

Overview

Tools in MCP allow servers to expose executable functions that can be invoked by clients and used by LLMs to perform actions. Key aspects of tools include:

• Discovery: Clients can list available tools through the tools/list endpoint
• Invocation: Tools are called using the tools/call endpoint, where servers perform the requested operation and return results
• Flexibility: Tools can range from simple calculations to complex API interactions

Like resources, tools are identified by unique names and can include descriptions to guide their usage. However, unlike resources, tools represent dynamic operations that can modify state or interact with external systems.

Tool definition structure

Each tool is defined with the following structure:

{
  name: string;          // Unique identifier for the tool
  description?: string;  // Human-readable description
  inputSchema: {         // JSON Schema for the tool's parameters
    type: "object",
    properties: { ... }  // Tool-specific parameters
  }
}

Implementing tools

Here's an example of implementing a basic tool in an MCP server:

```typescript const server = new Server({ name: "example-server", version: "1.0.0" }, { capabilities: { tools: {} } });

// Define available tools
server.setRequestHandler(ListToolsRequestSchema, async () => {
  return {
    tools: [{
      name: "calculate_sum",
      description: "Add two numbers together",
      inputSchema: {
        type: "object",
        properties: {
          a: { type: "number" },
          b: { type: "number" }
        },
        required: ["a", "b"]
      }
    }]
  };
});

// Handle tool execution
server.setRequestHandler(CallToolRequestSchema, async (request) => {
  if (request.params.name === "calculate_sum") {
    const { a, b } = request.params.arguments;
    return {
      content: [
        {
          type: "text",
          text: String(a + b)
        }
      ]
    };
  }
  throw new Error("Tool not found");
});
```

```python app = Server("example-server")

@app.list_tools()
async def list_tools() -> list[types.Tool]:
    return [
        types.Tool(
            name="calculate_sum",
            description="Add two numbers together",
            inputSchema={
                "type": "object",
                "properties": {
                    "a": {"type": "number"},
                    "b": {"type": "number"}
                },
                "required": ["a", "b"]
            }
        )
    ]

@app.call_tool()
async def call_tool(
    name: str,
    arguments: dict
) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
    if name == "calculate_sum":
        a = arguments["a"]
        b = arguments["b"]
        result = a + b
        return [types.TextContent(type="text", text=str(result))]
    raise ValueError(f"Tool not found: {name}")
```

Example tool patterns

Here are some examples of types of tools that a server could provide:

System operations

Tools that interact with the local system:

{
  name: "execute_command",
  description: "Run a shell command",
  inputSchema: {
    type: "object",
    properties: {
      command: { type: "string" },
      args: { type: "array", items: { type: "string" } }
    }
  }
}

API integrations

Tools that wrap external APIs:

{
  name: "github_create_issue",
  description: "Create a GitHub issue",
  inputSchema: {
    type: "object",
    properties: {
      title: { type: "string" },
      body: { type: "string" },
      labels: { type: "array", items: { type: "string" } }
    }
  }
}

Data processing

Tools that transform or analyze data:

{
  name: "analyze_csv",
  description: "Analyze a CSV file",
  inputSchema: {
    type: "object",
    properties: {
      filepath: { type: "string" },
      operations: {
        type: "array",
        items: {
          enum: ["sum", "average", "count"]
        }
      }
    }
  }
}

Best practices

When implementing tools:

1. Provide clear, descriptive names and descriptions
2. Use detailed JSON Schema definitions for parameters
3. Include examples in tool descriptions to demonstrate how the model should use them
4. Implement proper error handling and validation
5. Use progress reporting for long operations
6. Keep tool operations focused and atomic
7. Document expected return value structures
8. Implement proper timeouts
9. Consider rate limiting for resource-intensive operations
10. Log tool usage for debugging and monitoring

Security considerations

When exposing tools:

Input validation

• Validate all parameters against the schema
• Sanitize file paths and system commands
• Validate URLs and external identifiers
• Check parameter sizes and ranges
• Prevent command injection

Access control

• Implement authentication where needed
• Use appropriate authorization checks
• Audit tool usage
• Rate limit requests
• Monitor for abuse

Error handling

• Don't expose internal errors to clients
• Log security-relevant errors
• Handle timeouts appropriately
• Clean up resources after errors
• Validate return values

Tool discovery and updates

MCP supports dynamic tool discovery:

1. Clients can list available tools at any time
2. Servers can notify clients when tools change using notifications/tools/list_changed
3. Tools can be added or removed during runtime
4. Tool definitions can be updated (though this should be done carefully)

Error handling

Tool errors should be reported within the result object, not as MCP protocol-level errors. This allows the LLM to see and potentially handle the error. When a tool encounters an error:

1. Set isError to true in the result
2. Include error details in the content array

Here's an example of proper error handling for tools:

```typescript try { // Tool operation const result = performOperation(); return { content: [ { type: "text", text: `Operation successful: ${result}` } ] }; } catch (error) { return { isError: true, content: [ { type: "text", text: `Error: ${error.message}` } ] }; } ``` ```python try: # Tool operation result = perform_operation() return types.CallToolResult( content=[ types.TextContent( type="text", text=f"Operation successful: {result}" ) ] ) except Exception as error: return types.CallToolResult( isError=True, content=[ types.TextContent( type="text", text=f"Error: {str(error)}" ) ] ) ```

This approach allows the LLM to see that an error occurred and potentially take corrective action or request human intervention.

Testing tools

A comprehensive testing strategy for MCP tools should cover:

• Functional testing: Verify tools execute correctly with valid inputs and handle invalid inputs appropriately
• Integration testing: Test tool interaction with external systems using both real and mocked dependencies
• Security testing: Validate authentication, authorization, input sanitization, and rate limiting
• Performance testing: Check behavior under load, timeout handling, and resource cleanup
• Error handling: Ensure tools properly report errors through the MCP protocol and clean up resources

Transports

Source: https://modelcontextprotocol.io/docs/concepts/transports

Learn about MCP's communication mechanisms

Transports in the Model Context Protocol (MCP) provide the foundation for communication between clients and servers. A transport handles the underlying mechanics of how messages are sent and received.

Message Format

MCP uses JSON-RPC 2.0 as its wire format. The transport layer is responsible for converting MCP protocol messages into JSON-RPC format for transmission and converting received JSON-RPC messages back into MCP protocol messages.

There are three types of JSON-RPC messages used:

Requests

{
  jsonrpc: "2.0",
  id: number | string,
  method: string,
  params?: object
}

Responses

{
  jsonrpc: "2.0",
  id: number | string,
  result?: object,
  error?: {
    code: number,
    message: string,
    data?: unknown
  }
}

Notifications

{
  jsonrpc: "2.0",
  method: string,
  params?: object
}

Built-in Transport Types

MCP includes two standard transport implementations:

Standard Input/Output (stdio)

The stdio transport enables communication through standard input and output streams. This is particularly useful for local integrations and command-line tools.

Use stdio when:

• Building command-line tools
• Implementing local integrations
• Needing simple process communication
• Working with shell scripts

```typescript const server = new Server({ name: "example-server", version: "1.0.0" }, { capabilities: {} });

const transport = new StdioServerTransport();
await server.connect(transport);
```

```typescript const client = new Client({ name: "example-client", version: "1.0.0" }, { capabilities: {} });

const transport = new StdioClientTransport({
  command: "./server",
  args: ["--option", "value"]
});
await client.connect(transport);
```

```python app = Server("example-server")

async with stdio_server() as streams:
    await app.run(
        streams[0],
        streams[1],
        app.create_initialization_options()
    )
```

```python params = StdioServerParameters( command="./server", args=["--option", "value"] )

async with stdio_client(params) as streams:
    async with ClientSession(streams[0], streams[1]) as session:
        await session.initialize()
```

Server-Sent Events (SSE)

SSE transport enables server-to-client streaming with HTTP POST requests for client-to-server communication.

Use SSE when:

• Only server-to-client streaming is needed
• Working with restricted networks
• Implementing simple updates

```typescript import express from "express";

const app = express();

const server = new Server({
  name: "example-server",
  version: "1.0.0"
}, {
  capabilities: {}
});

let transport: SSEServerTransport | null = null;

app.get("/sse", (req, res) => {
  transport = new SSEServerTransport("/messages", res);
  server.connect(transport);
});

app.post("/messages", (req, res) => {
  if (transport) {
    transport.handlePostMessage(req, res);
  }
});

app.listen(3000);
```

```typescript const client = new Client({ name: "example-client", version: "1.0.0" }, { capabilities: {} });

const transport = new SSEClientTransport(
  new URL("http://localhost:3000/sse")
);
await client.connect(transport);
```

```python from mcp.server.sse import SseServerTransport from starlette.applications import Starlette from starlette.routing import Route

app = Server("example-server")
sse = SseServerTransport("/messages")

async def handle_sse(scope, receive, send):
    async with sse.connect_sse(scope, receive, send) as streams:
        await app.run(streams[0], streams[1], app.create_initialization_options())

async def handle_messages(scope, receive, send):
    await sse.handle_post_message(scope, receive, send)

starlette_app = Starlette(
    routes=[
        Route("/sse", endpoint=handle_sse),
        Route("/messages", endpoint=handle_messages, methods=["POST"]),
    ]
)
```

```python async with sse_client("http://localhost:8000/sse") as streams: async with ClientSession(streams[0], streams[1]) as session: await session.initialize() ```

Custom Transports

MCP makes it easy to implement custom transports for specific needs. Any transport implementation just needs to conform to the Transport interface:

You can implement custom transports for:

• Custom network protocols
• Specialized communication channels
• Integration with existing systems
• Performance optimization

```typescript interface Transport { // Start processing messages start(): Promise;

  // Send a JSON-RPC message
  send(message: JSONRPCMessage): Promise<void>;

  // Close the connection
  close(): Promise<void>;

  // Callbacks
  onclose?: () => void;
  onerror?: (error: Error) => void;
  onmessage?: (message: JSONRPCMessage) => void;
}
```

Note that while MCP Servers are often implemented with asyncio, we recommend implementing low-level interfaces like transports with `anyio` for wider compatibility.

```python
@contextmanager
async def create_transport(
    read_stream: MemoryObjectReceiveStream[JSONRPCMessage | Exception],
    write_stream: MemoryObjectSendStream[JSONRPCMessage]
):
    """
    Transport interface for MCP.

    Args:
        read_stream: Stream to read incoming messages from
        write_stream: Stream to write outgoing messages to
    """
    async with anyio.create_task_group() as tg:
        try:
            # Start processing messages
            tg.start_soon(lambda: process_messages(read_stream))

            # Send messages
            async with write_stream:
                yield write_stream

        except Exception as exc:
            # Handle errors
            raise exc
        finally:
            # Clean up
            tg.cancel_scope.cancel()
            await write_stream.aclose()
            await read_stream.aclose()
```

Error Handling

Transport implementations should handle various error scenarios:

1. Connection errors
2. Message parsing errors
3. Protocol errors
4. Network timeouts
5. Resource cleanup

Example error handling:

```typescript class ExampleTransport implements Transport { async start() { try { // Connection logic } catch (error) { this.onerror?.(new Error(`Failed to connect: ${error}`)); throw error; } }

  async send(message: JSONRPCMessage) {
    try {
      // Sending logic
    } catch (error) {
      this.onerror?.(new Error(`Failed to send message: ${error}`));
      throw error;
    }
  }
}
```

Note that while MCP Servers are often implemented with asyncio, we recommend implementing low-level interfaces like transports with `anyio` for wider compatibility.

```python
@contextmanager
async def example_transport(scope: Scope, receive: Receive, send: Send):
    try:
        # Create streams for bidirectional communication
        read_stream_writer, read_stream = anyio.create_memory_object_stream(0)
        write_stream, write_stream_reader = anyio.create_memory_object_stream(0)

        async def message_handler():
            try:
                async with read_stream_writer:
                    # Message handling logic
                    pass
            except Exception as exc:
                logger.error(f"Failed to handle message: {exc}")
                raise exc

        async with anyio.create_task_group() as tg:
            tg.start_soon(message_handler)
            try:
                # Yield streams for communication
                yield read_stream, write_stream
            except Exception as exc:
                logger.error(f"Transport error: {exc}")
                raise exc
            finally:
                tg.cancel_scope.cancel()
                await write_stream.aclose()
                await read_stream.aclose()
    except Exception as exc:
        logger.error(f"Failed to initialize transport: {exc}")
        raise exc
```

Best Practices

When implementing or using MCP transport:

1. Handle connection lifecycle properly
2. Implement proper error handling
3. Clean up resources on connection close
4. Use appropriate timeouts
5. Validate messages before sending
6. Log transport events for debugging
7. Implement reconnection logic when appropriate
8. Handle backpressure in message queues
9. Monitor connection health
10. Implement proper security measures

Security Considerations

When implementing transport:

Authentication and Authorization

• Implement proper authentication mechanisms
• Validate client credentials
• Use secure token handling
• Implement authorization checks

Data Security

• Use TLS for network transport
• Encrypt sensitive data
• Validate message integrity
• Implement message size limits
• Sanitize input data

Network Security

• Implement rate limiting
• Use appropriate timeouts
• Handle denial of service scenarios
• Monitor for unusual patterns
• Implement proper firewall rules

Debugging Transport

Tips for debugging transport issues:

1. Enable debug logging
2. Monitor message flow
3. Check connection states
4. Validate message formats
5. Test error scenarios
6. Use network analysis tools
7. Implement health checks
8. Monitor resource usage
9. Test edge cases
10. Use proper error tracking

Debugging

Source: https://modelcontextprotocol.io/docs/tools/debugging

A comprehensive guide to debugging Model Context Protocol (MCP) integrations

Effective debugging is essential when developing MCP servers or integrating them with applications. This guide covers the debugging tools and approaches available in the MCP ecosystem.

This guide is for macOS. Guides for other platforms are coming soon.

Debugging tools overview

MCP provides several tools for debugging at different levels:

1. MCP Inspector

   • Interactive debugging interface
   • Direct server testing
   • See the Inspector guide for details

2. Claude Desktop Developer Tools

   • Integration testing
   • Log collection
   • Chrome DevTools integration

3. Server Logging

   • Custom logging implementations
   • Error tracking
   • Performance monitoring

Debugging in Claude Desktop

Checking server status

The Claude.app interface provides basic server status information:

1. Click the <img src="https://mintlify.s3.us-west-1.amazonaws.com/mcp/images/claude-desktop-mcp-plug-icon.svg" style={{display: 'inline', margin: 0, height: '1.3em'}} /> icon to view:

   • Connected servers
   • Available prompts and resources

2. Click the <img src="https://mintlify.s3.us-west-1.amazonaws.com/mcp/images/claude-desktop-mcp-hammer-icon.svg" style={{display: 'inline', margin: 0, height: '1.3em'}} /> icon to view:

   • Tools made available to the model

Viewing logs

Review detailed MCP logs from Claude Desktop:

# Follow logs in real-time
tail -n 20 -F ~/Library/Logs/Claude/mcp*.log

The logs capture:

• Server connection events
• Configuration issues
• Runtime errors
• Message exchanges

Using Chrome DevTools

Access Chrome's developer tools inside Claude Desktop to investigate client-side errors:

1. Create a developer_settings.json file with allowDevTools set to true:

echo '{"allowDevTools": true}' > ~/Library/Application\ Support/Claude/developer_settings.json

2. Open DevTools: Command-Option-Shift-i

Note: You'll see two DevTools windows:

• Main content window
• App title bar window

Use the Console panel to inspect client-side errors.

Use the Network panel to inspect:

• Message payloads
• Connection timing

Common issues

Working directory

When using MCP servers with Claude Desktop:

• The working directory for servers launched via claude_desktop_config.json may be undefined (like / on macOS) since Claude Desktop could be started from anywhere
• Always use absolute paths in your configuration and .env files to ensure reliable operation
• For testing servers directly via command line, the working directory will be where you run the command

For example in claude_desktop_config.json, use:

{
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/username/data"]
}

Instead of relative paths like ./data

Environment variables

MCP servers inherit only a subset of environment variables automatically, like USER, HOME, and PATH.

To override the default variables or provide your own, you can specify an env key in claude_desktop_config.json:

{
  "myserver": {
    "command": "mcp-server-myapp",
    "env": {
      "MYAPP_API_KEY": "some_key",
    }
  }
}

Server initialization

Common initialization problems:

1. Path Issues

   • Incorrect server executable path
   • Missing required files
   • Permission problems
   • Try using an absolute path for command

2. Configuration Errors

   • Invalid JSON syntax
   • Missing required fields
   • Type mismatches

3. Environment Problems

   • Missing environment variables
   • Incorrect variable values
   • Permission restrictions

Connection problems

When servers fail to connect:

1. Check Claude Desktop logs
2. Verify server process is running
3. Test standalone with Inspector
4. Verify protocol compatibility

Implementing logging

Server-side logging

When building a server that uses the local stdio transport, all messages logged to stderr (standard error) will be captured by the host application (e.g., Claude Desktop) automatically.

Local MCP servers should not log messages to stdout (standard out), as this will interfere with protocol operation.

For all transports, you can also provide logging to the client by sending a log message notification:

```python server.request_context.session.send_log_message( level="info", data="Server started successfully", ) ``` ```typescript server.sendLoggingMessage({ level: "info", data: "Server started successfully", }); ```

Important events to log:

• Initialization steps
• Resource access
• Tool execution
• Error conditions
• Performance metrics

Client-side logging

In client applications:

1. Enable debug logging
2. Monitor network traffic
3. Track message exchanges
4. Record error states

Debugging workflow

Development cycle

1. Initial Development

   • Use Inspector for basic testing
   • Implement core functionality
   • Add logging points

2. Integration Testing

   • Test in Claude Desktop
   • Monitor logs
   • Check error handling

Testing changes

To test changes efficiently:

• Configuration changes: Restart Claude Desktop
• Server code changes: Use Command-R to reload
• Quick iteration: Use Inspector during development

Best practices

Logging strategy

1. Structured Logging

   • Use consistent formats
   • Include context
   • Add timestamps
   • Track request IDs

2. Error Handling

   • Log stack traces
   • Include error context
   • Track error patterns
   • Monitor recovery

3. Performance Tracking

   • Log operation timing
   • Monitor resource usage
   • Track message sizes
   • Measure latency

Security considerations

When debugging:

1. Sensitive Data

   • Sanitize logs
   • Protect credentials
   • Mask personal information

2. Access Control

   • Verify permissions
   • Check authentication
   • Monitor access patterns

Getting help

When encountering issues:

1. First Steps

   • Check server logs
   • Test with Inspector
   • Review configuration
   • Verify environment

2. Support Channels

   • GitHub issues
   • GitHub discussions

3. Providing Information

   • Log excerpts
   • Configuration files
   • Steps to reproduce
   • Environment details

Next steps

Learn to use the MCP Inspector

Inspector

Source: https://modelcontextprotocol.io/docs/tools/inspector

In-depth guide to using the MCP Inspector for testing and debugging Model Context Protocol servers

The MCP Inspector is an interactive developer tool for testing and debugging MCP servers. While the Debugging Guide covers the Inspector as part of the overall debugging toolkit, this document provides a detailed exploration of the Inspector's features and capabilities.

Getting started

Installation and basic usage

The Inspector runs directly through npx without requiring installation:

npx @modelcontextprotocol/inspector <command>

npx @modelcontextprotocol/inspector <command> <arg1> <arg2>

Inspecting servers from NPM or PyPi

A common way to start server packages from NPM or PyPi.

```bash npx -y @modelcontextprotocol/inspector npx # For example npx -y @modelcontextprotocol/inspector npx server-postgres postgres://127.0.0.1/testdb ``` ```bash npx @modelcontextprotocol/inspector uvx # For example npx @modelcontextprotocol/inspector uvx mcp-server-git --repository ~/code/mcp/servers.git ```

Inspecting locally developed servers

To inspect servers locally developed or downloaded as a repository, the most common way is:

```bash npx @modelcontextprotocol/inspector node path/to/server/index.js args... ``` ```bash npx @modelcontextprotocol/inspector \ uv \ --directory path/to/server \ run \ package-name \ args... ```

Please carefully read any attached README for the most accurate instructions.

Feature overview

The Inspector provides several features for interacting with your MCP server:

Server connection pane

• Allows selecting the transport for connecting to the server
• For local servers, supports customizing the command-line arguments and environment

Resources tab

• Lists all available resources
• Shows resource metadata (MIME types, descriptions)
• Allows resource content inspection
• Supports subscription testing

Prompts tab

• Displays available prompt templates
• Shows prompt arguments and descriptions
• Enables prompt testing with custom arguments
• Previews generated messages

Tools tab

• Lists available tools
• Shows tool schemas and descriptions
• Enables tool testing with custom inputs
• Displays tool execution results

Notifications pane

• Presents all logs recorded from the server
• Shows notifications received from the server

Best practices

Development workflow

1. Start Development

   • Launch Inspector with your server
   • Verify basic connectivity
   • Check capability negotiation

2. Iterative testing

   • Make server changes
   • Rebuild the server
   • Reconnect the Inspector
   • Test affected features
   • Monitor messages

3. Test edge cases

   • Invalid inputs
   • Missing prompt arguments
   • Concurrent operations
   • Verify error handling and error responses

Next steps

Check out the MCP Inspector source code Learn about broader debugging strategies

Example Servers

Source: https://modelcontextprotocol.io/examples

A list of example servers and implementations

This page showcases various Model Context Protocol (MCP) servers that demonstrate the protocol's capabilities and versatility. These servers enable Large Language Models (LLMs) to securely access tools and data sources.

Reference implementations

These official reference servers demonstrate core MCP features and SDK usage:

Data and file systems

• Filesystem - Secure file operations with configurable access controls
• PostgreSQL - Read-only database access with schema inspection capabilities
• SQLite - Database interaction and business intelligence features
• Google Drive - File access and search capabilities for Google Drive

Development tools

• Git - Tools to read, search, and manipulate Git repositories
• GitHub - Repository management, file operations, and GitHub API integration
• GitLab - GitLab API integration enabling project management
• Sentry - Retrieving and analyzing issues from Sentry.io

Web and browser automation

• Brave Search - Web and local search using Brave's Search API
• Fetch - Web content fetching and conversion optimized for LLM usage
• Puppeteer - Browser automation and web scraping capabilities

Productivity and communication

• Slack - Channel management and messaging capabilities
• Google Maps - Location services, directions, and place details
• Memory - Knowledge graph-based persistent memory system

AI and specialized tools

• EverArt - AI image generation using various models
• Sequential Thinking - Dynamic problem-solving through thought sequences
• AWS KB Retrieval - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime

Official integrations

These MCP servers are maintained by companies for their platforms:

• Axiom - Query and analyze logs, traces, and event data using natural language
• Browserbase - Automate browser interactions in the cloud
• Cloudflare - Deploy and manage resources on the Cloudflare developer platform
• E2B - Execute code in secure cloud sandboxes
• Neon - Interact with the Neon serverless Postgres platform
• Obsidian Markdown Notes - Read and search through Markdown notes in Obsidian vaults
• Qdrant - Implement semantic memory using the Qdrant vector search engine
• Raygun - Access crash reporting and monitoring data
• Search1API - Unified API for search, crawling, and sitemaps
• Stripe - Interact with the Stripe API
• Tinybird - Interface with the Tinybird serverless ClickHouse platform
• Weaviate - Enable Agentic RAG through your Weaviate collection(s)

Community highlights

A growing ecosystem of community-developed servers extends MCP's capabilities:

• Docker - Manage containers, images, volumes, and networks
• Kubernetes - Manage pods, deployments, and services
• Linear - Project management and issue tracking
• Snowflake - Interact with Snowflake databases
• Spotify - Control Spotify playback and manage playlists
• Todoist - Task management integration

Note: Community servers are untested and should be used at your own risk. They are not affiliated with or endorsed by Anthropic.

For a complete list of community servers, visit the MCP Servers Repository.

Getting started

Using reference servers

TypeScript-based servers can be used directly with npx:

npx -y @modelcontextprotocol/server-memory

Python-based servers can be used with uvx (recommended) or pip:

# Using uvx
uvx mcp-server-git

# Using pip
pip install mcp-server-git
python -m mcp_server_git

Configuring with Claude

To use an MCP server with Claude, add it to your configuration:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    },
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/files"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

Additional resources

• MCP Servers Repository - Complete collection of reference implementations and community servers
• Awesome MCP Servers - Curated list of MCP servers
• MCP CLI - Command-line inspector for testing MCP servers
• MCP Get - Tool for installing and managing MCP servers
• Supergateway - Run MCP stdio servers over SSE

Visit our GitHub Discussions to engage with the MCP community.

Introduction

Source: https://modelcontextprotocol.io/introduction

Get started with the Model Context Protocol (MCP)

Java SDK released! Check out what else is new.

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

Why MCP?

MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:

• A growing list of pre-built integrations that your LLM can directly plug into
• The flexibility to switch between LLM providers and vendors
• Best practices for securing your data within your infrastructure

General architecture

At its core, MCP follows a client-server architecture where a host application can connect to multiple servers:

flowchart LR
    subgraph "Your Computer"
        Host["Host with MCP Client\n(Claude, IDEs, Tools)"]
        S1["MCP Server A"]
        S2["MCP Server B"]
        S3["MCP Server C"]
        Host <-->|"MCP Protocol"| S1
        Host <-->|"MCP Protocol"| S2
        Host <-->|"MCP Protocol"| S3
        S1 <--> D1[("Local\nData Source A")]
        S2 <--> D2[("Local\nData Source B")]
    end
    subgraph "Internet"
        S3 <-->|"Web APIs"| D3[("Remote\nService C")]
    end

• MCP Hosts: Programs like Claude Desktop, IDEs, or AI tools that want to access data through MCP
• MCP Clients: Protocol clients that maintain 1:1 connections with servers
• MCP Servers: Lightweight programs that each expose specific capabilities through the standardized Model Context Protocol
• Local Data Sources: Your computer's files, databases, and services that MCP servers can securely access
• Remote Services: External systems available over the internet (e.g., through APIs) that MCP servers can connect to

Get started

Choose the path that best fits your needs:

Quick Starts

Get started building your own server to use in Claude for Desktop and other clients Get started building your own client that can integrate with all MCP servers Get started using pre-built servers in Claude for Desktop

Examples

Check out our gallery of official MCP servers and implementations View the list of clients that support MCP integrations

Tutorials

Learn how to use LLMs like Claude to speed up your MCP development Learn how to effectively debug MCP servers and integrations Test and inspect your MCP servers with our interactive debugging tool