starlette_mcp_sse

English | 简体中文

A Server-Sent Events (SSE) implementation using Starlette framework with Model Context Protocol (MCP) integration.

The Model Context Protocol (MCP) is an open standard that enables AI models to interact with external tools and data sources. MCP solves several key challenges in AI development:

• Context limitations: Allows models to access up-to-date information beyond their training data
• Tool integration: Provides a standardized way for models to use external tools and APIs
• Interoperability: Creates a common interface between different AI models and tools
• Extensibility: Makes it easy to add new capabilities to AI systems without retraining

This project demonstrates how to implement MCP using Server-Sent Events (SSE) in a Starlette web application.

This project demonstrates how to implement Server-Sent Events (SSE) using the Starlette framework while integrating Model Context Protocol (MCP) functionality. The key feature is the seamless integration of MCP's SSE capabilities within a full-featured Starlette web application that includes custom routes.

• Server-Sent Events (SSE) implementation with MCP
• Starlette framework integration with custom routes
• Unified web application with both MCP and standard web endpoints
• Customizable route structure
• Clean separation of concerns between MCP and web functionality

This project showcases a modular architecture that:

1. Integrates MCP SSE endpoints (/sse and /messages/) into a Starlette application
2. Provides standard web routes (/, /about, /status, /docs)
3. Demonstrates how to maintain separation between MCP functionality and web routes

Install UV Package Manager - A fast Python package installer written in Rust:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Run the application directly without cloning the repository using UV's execution tool:

uvx --from git+https://github.com/panz2018/starlette_mcp_sse.git start

Create an isolated Python environment for the project:

uv venv

Activate the virtual environment to use it:

.venv\Scripts\activate

Install all required packages:

uv pip install -r pyproject.toml

Launch the integrated Starlette server with MCP SSE functionality:

python src/server.py

or

uv run start

After starting the server (using either Option 1 or Option 2), the following endpoints will be available:

• Main server: http://localhost:8000
• Standard web routes:
  • Home page: http://localhost:8000/
  • About page: http://localhost:8000/about
  • Status API: http://localhost:8000/status
  • Documentation: http://localhost:8000/docs
• MCP SSE endpoints:
  • SSE endpoint: http://localhost:8000/sse
  • Message posting: http://localhost:8000/messages/

For testing and debugging MCP functionality, use the MCP Inspector:

mcp dev ./src/weather.py

1. Open MCP Inspector at http://localhost:5173
2. Configure the connection:
   • Set Transport Type to SSE
   • Enter URL: http://localhost:8000/sse
   • Click Connect

1. Navigate to Tools section
2. Click List Tools to see available functions:
   • get_alerts : Get weather alerts
   • get_forcast : Get weather forecast
3. Select a function
4. Enter required parameters
5. Click Run Tool to execute

The application structure makes it easy to add new routes:

1. Define new route handlers in routes.py
2. Add routes to the routes list in routes.py
3. The main application will automatically include these routes

The MCP SSE functionality is integrated in server.py through:

• Creating an SSE transport
• Setting up an SSE handler
• Adding MCP routes to the Starlette application

To use this MCP server with the Continue VS Code extension, add the following configuration to your Continue settings:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "name": "weather",
          "type": "sse",
          "url": "http://localhost:8000/sse"
        }
      }
    ]
  }
}