mcp_hackathon/README.md

mcp_hackathon

Data Generation Server for ICD Code Finetuning

This MCP server provides tools for finetuning models to improve medical ICD-10 code prediction accuracy.

Overview

The Data Generation Server is a Model Control Protocol (MCP) server that facilitates:

1. Model Probing: Evaluating model performance on ICD-10 code prediction
2. Synthetic Data Generation: Creating training data for model finetuning

Set up the server

{
  "mcpServers": {
      "data_gen_server": {
          "command": "<base_dir>/.local/bin/uv",
          "args": [
              "--directory",
              "<base_dir>/mcp_hackathon/data_gen_server",
              "run",
              "data_gen_server.py"
          ]
      }
  }
}

To use MCP tools in Cursor, you need to have your MCP server configured and running. Here's how to use them:

1. Verify MCP Configuration

First, make sure your MCP configuration is set up correctly in /Users/john/.cursor/mcp.json: Read file: /Users/john/.cursor/mcp.json Great! You have two MCP servers configured. Here's how to use them:

2. How MCP Tools Work in Cursor

MCP tools in Cursor work through function calling. When you mention or request something that can be handled by your MCP tools, Cursor will automatically:

1. Detect when a task matches available MCP tools
2. Call the appropriate tool with the right parameters
3. Present the results to you

3. Using MCP Tools

Method 1: Direct Requests

You can directly ask me to use the tools by mentioning what you want to do:

Examples:

• "List all available data generation templates"
• "Generate city information for San Francisco, New York, and Los Angeles"
• "Run the starfish template with this data: [your data]"
• "Generate synthetic data for ICD codes"

Method 2: Specific Tool References

You can reference tools by name if you know them:

Let me check what tools are available from your MCP servers: Ran tool Ran tool Perfect! Your MCP tools are working. Here's how to use them effectively:

4. Available Tools and Usage Examples

From starfish_gen_template server:

• List templates: "Show me all available data generation templates"
• Generate city info: "Generate information for cities: San Francisco, New York"
• Run templates: "Run the starfish/generate_by_topic template"

From starfish_data_gen_server server:

• Generate data: "Generate 10 datapoints of synthetic data"
• Probe model: "Test the model with 5 ICD code datapoints"
• Finetune model: "Finetune the model for ICD code classification"

5. How to Use MCP Tools in Practice

Example 1: Generate Data

You: "Generate 10 synthetic datapoints for training"

I will automatically call the appropriate MCP tool.

Example 2: List Available Templates

You: "What data generation templates are available?"

Example 3: Run Specific Template

You: "Run the generate_by_topic template with topics: AI, Machine Learning"

6. Best Practices

1. Be specific about what you want to accomplish
2. Provide data when needed (I'll ask if unclear)
3. Check results and iterate if needed
4. Use natural language - no need for technical syntax

7. Restart Cursor (if needed)

If you just updated your MCP configuration, restart Cursor to ensure the tools are loaded:

1. Quit Cursor completely
2. Reopen it
3. The MCP tools should now be available

Try It Now!

You can test the MCP tools by asking me to:

• "List all available data generation templates"
• "Generate some sample data"
• "Show me what tools are available"

The tools will work seamlessly in our conversation - just tell me what you want to accomplish!