mcp-calculator

# Tool List A powerful interface for extending AI capabilities through remote control, calculations, email operations, knowledge search, and more. ## Overview MCP (Model Context Protocol) is a protocol that allows servers to expose tools that can be invoked by language models. Tools enable models to interact with external systems, such as querying databases, calling APIs, or performing computations. Each tool is uniquely identified by a name and includes metadata describing its schema. ## Features - 🔌 Bidirectional communication between AI and external tools - 🔄 Automatic reconnection with exponential backoff - 📊 Real-time data streaming - 🛠️ Easy-to-use tool creation interface - 🔒 Secure WebSocket communication - ⚙️ Multiple transport types support (stdio/sse/http) ## Quick Start 1. Install dependencies: ```bash pip install -r requirements.txt ``` 2. Set up environment variables: ```bash export MCP_ENDPOINT=<your_mcp_endpoint> ``` 3. Run the calculator example: ```bash python mcp_pipe.py calculator.py ``` Or run all configured servers: ```bash python mcp_pipe.py ``` *Requires `mcp_config.json` configuration file with server definitions (supports stdio/sse/http transport types)* ## Project Structure - `mcp_pipe.py`: Main communication pipe that handles WebSocket connections and process management - `calculator.py`: Example MCP tool implementation for mathematical calculations - `requirements.txt`: Project dependencies ## Config-driven Servers Edit the `mcp_config.json` file to configure the server list (you can also set the `MCP_CONFIG` environment variable to point to another configuration file). Configuration instructions: - Start all configured services without parameters (automatically skip entries with `disabled: true`) - Run a single local script file with parameters - `type=stdio` starts directly; `type=sse/http` is proxied through `python -m mcp_proxy` ## Creating Your Own MCP Tools Here's a simple example of creating an MCP tool: ```python from mcp.server.fastmcp import FastMCP mcp = FastMCP("YourToolName") @mcp.tool() def your_tool(parameter: str) -> dict: """Tool description here""" # Your implementation return {"success": True, "result": result} if __name__ == "__main__": mcp.run(transport="stdio") ``` ## Use Cases - Mathematical calculations - Email operations - Knowledge base search - Remote device control - Data processing - Custom tool integration ## Requirements - Python 3.7+ - websockets>=11.0.3 - python-dotenv>=1.0.0 - mcp>=1.8.1 - pydantic>=2.11.4 - mcp-proxy>=0.8.2 ## Contributing Contributions are welcome! Please feel free to submit a Pull Request. ## License This project is licensed under the MIT License - see the LICENSE file for details. ## Acknowledgments - Thanks to all contributors who have helped shape this project - Inspired by the need for extensible AI capabilities