xiaozhi-mcp

# xiaozhi MCP Aggregate 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. ## Tools - **conversation_dingtalk**: Send conversation to dingtalk - **email_qq**: Send email with qq mail account - **system**: Get server status - **web_webpilot**: Web search by WebPilot ## 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 ## Quick Start 1. Install dependencies: ```bash python3 -m venv venv source venv/bin/activate pip3 install -r requirements.txt ``` 2. Set up environment variables: ```bash # Copy the .env.example file to your own configuration file, e.g., .env.xiaozhi1 ``` 3. Run the example: ```bash # You can run different XiaoZhi MCP access points through different configuration files python mcp_pipe.py aggregate.py --env-file .env.xiaozhi1 ``` ## Creating Your Own MCP Tools Here's a simple example of creating an MCP tool: - According to the example in the tools folder, create your own tool - The tool name is distinguished by function_channel, for example, email_google indicates that it is a Google Mail MCP tool - Register your tool in aggregate.py - Configure the environment variables for your tool in the .env.xxx file (if any) - If you want to contribute code, you also need to add the environment variables for your tool (if any) in the .env.example file ## Use Cases - Mathematical calculations - Email operations - Knowledge base search - Remote device control - Data processing - Custom tool integration ## Requirements - Python 3.10+ - websockets>=11.0.3 - python-dotenv>=1.0.0 - mcp>=1.8.1 - pydantic>=2.11.4 ## FAQ - MCP_PIPE - ERROR - Connection error: python-socks is required to use a SOCKS proxy ```text 关闭电脑的系统代理 Close the system proxy on your computer ``` ## 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 - https://github.com/78/mcp-calculator - Thanks to all contributors who have helped shape this project - Inspired by the need for extensible AI capabilities