✨ litemcp

A minimal, lightweight client designed to simplify SDK adoption into MCP.

litemcp enables rapid and intuitive integration of various AI SDKs (e.g., LangChain, Agent SDK) into your MCP projects, emphasizing simplicity, flexibility, and minimal dependencies.

🌟 Key Features

• Simplicity: Streamlined interfaces ensure easy integration.
• Flexibility: Quickly adopt diverse SDKs with minimal effort.
• Lightweight: Designed with minimal dependencies to maximize clarity and performance.

🚚 Installation

Install via pip:

pip install litemcp

🚦 Quick Start

litemcp allows you to integrate tools from an MCP server into various LLM runtimes, including the OpenAI Agent SDK, LangChain, and direct OpenAI API calls. The examples demonstrate integration with OpenAI Agent SDK, LangChain, and direct OpenAI API calls, showcasing how to use MCPServerManager to bind tools and execute them. It also provides an optional tool call validator for enhanced security, allowing custom validation functions to control MCP tool calls.

🧰 Tool Call Validator(Optional)

You can add a custom validation function to control MCP tool calls.

⚙ MCP Configuration Schema

Configure your MCP environment with optional server enabling and tool exclusion. The configuration schema uses a JSON format to define MCP servers, their commands, arguments, and options to exclude specific tools or require confirmation for certain actions.

📚 Documentation

Detailed documentation coming soon!

🤝 Contributing

Contributions and suggestions are welcome! Please open an issue or submit a pull request.

📜 License

liteMCP is available under the MIT License.