Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@xiaozhi-mcpCalculate the monthly mortgage payment for a $500,000 loan at 6.5% interest"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
xiaozhi-mcp
A powerful interface for extending AI capabilities through remote control, calculations, email operations, knowledge search, and more.
About
MCP (Model Context Protocol) is a protocol that allows servers to expose tools that can be invoked by language models. This project provides a flexible framework for creating and managing MCP tools, supporting multiple transport types (stdio, SSE, HTTP) and enabling seamless integration between AI models and external systems.
Key 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)
How to Install
Using uv (Recommended)
Install uv:
Install dependencies:
Using pip
Install dependencies:
Requirements:
Python 3.10+
websockets>=16.0
python-dotenv>=1.2.1
mcp>=1.25.0
pydantic>=2.12.5
mcp-proxy>=0.11.0
fastmcp>=2.14.3
httpx>=0.28.1
yfinance>=1.0
pyyaml>=6.0.3
How to Run
Run All Configured Servers
Start all enabled servers from the configuration file:
Run a Single Server Script
Run a specific server script directly:
Run with Docker
Using Docker Compose (Recommended)
Using Docker directly
Building and Pushing Docker Images
Build and push to registry:
Example - Aliyun Container Registry:
Using the provided script:
For more Docker build and push options, see docs/DOCKER_BUILD_PUSH.md.
For more Docker deployment options, see docs/DEPLOYMENT.md.
Configs
Configuration files use YAML format:
mcp_config.yaml- Main configuration file
Configuration Structure
Edit mcp_config.yaml to configure your MCP endpoint and servers:
For detailed configuration examples, see docs/CONFIG.md.
Config Loading Priority
MCP_CONFIGenvironment variable (if set, used directly - backward compatibility)mcp_config.yaml(default configuration file)mcp_config.json(fallback, backward compatibility)
Thanks To
Thanks to all contributors who have helped shape this project
Inspired by the need for extensible AI capabilities
Built on top of the MCP (Model Context Protocol) specification
License
This project is licensed under the MIT License - see the LICENSE file for details.