python-sdk
Official Python SDK for Model Context Protocol, used to build MCP servers and clients.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 23.4k
- Source
- mcp-github
Overview
The MCP Python SDK is the official Python implementation of the Model Context Protocol (MCP). It enables developers to easily build MCP clients and servers, supporting standard transport protocols such as stdio, SSE, and Streamable HTTP. With this SDK, standardized context can be provided to LLMs while separating the responsibilities of context delivery and LLM interaction. Suitable for scenarios requiring context provision to AI models, such as building custom tools or resources.
Capabilities
- ▪Build MCP clients
- ▪Create MCP servers
- ▪Support multiple transport protocols
- ▪Handle MCP protocol messages
- ▪Manage lifecycle events
Use cases
Setup
Using uv: `uv add "mcp[cli]"`; using pip: `pip install "mcp[cli]"`
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How to install the MCP Python SDK?
Recommended: `uv add "mcp[cli]"`; or use pip: `pip install "mcp[cli]"`.
Which transport protocols does MCP support?
Supports stdio, SSE, and Streamable HTTP.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.