How to use Python SDK: what you can do with it

3 use cases

• Build an MCP server and test it in the Inspector

  Write a two-function server with the official SDK and try its tools in the MCP Inspector.

  • REPO modelcontextprotocol/python-sdk
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Beginner
  View prompt

  Using modelcontextprotocol/python-sdk, create a server.py that exposes <tools> and a resource for <data>. Open it with `uv run mcp dev server.py` and show me each tool working in the Inspector.

  Share Email me this

• Serve an MCP server over HTTP and call it from Python

  Run your server with Streamable HTTP and connect the SDK's Client to it with a URL.

  • REPO modelcontextprotocol/python-sdk
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Intermediate
  View prompt

  Using modelcontextprotocol/python-sdk, serve my server.py with `uv run mcp run server.py --transport streamable-http` and write a Python client that calls <tool> with <arguments> and prints the structured result.

  Share Email me this

• Try MCP commands without setting up a project

  Use uv to run the mcp CLI one-off, so you can test a server file without adding the SDK to a project.

  • REPO modelcontextprotocol/python-sdk
  • Claude Code
  • Codex
  • Cursor
  • Software and DevOps
  • Beginner
  View prompt

  Without creating a project, use the modelcontextprotocol/python-sdk CLI through `uv run --with "mcp[cli]" mcp ...` to open <server file> in the MCP Inspector and list what it exposes.

  Share Email me this

Quick start with Python SDK

1. Check you have what it needs: Python 3.11 or later; uv or pip; The cli extra for the mcp command-line tool.
2. Open modelcontextprotocol/python-sdk on GitHub and read the README and license.
3. Install with uv add "mcp[cli]"
4. Create server.py with an MCPServer, an add tool and a greeting resource, as in the README
5. Open it in the Inspector with uv run mcp dev server.py
6. Call add with a=1 and b=2 and check you get 3 back

These steps come from our top use case, Build an MCP server and test it in the Inspector, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for modelcontextprotocol/python-sdk

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Software and DevOps

About this repo

• Who it is forPython developers who want to build against the official MCP reference implementation.
• Why it is hot25k stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/modelcontextprotocol/python-sdk · Back to Hot repos

Requirements

• Python 3.11 or later
• uv or pip
• The cli extra for the mcp command-line tool
• Optional: the MCP Inspector, which mcp dev opens

Related repos

• Trended earlier REPO PrefectHQ/fastmcp Fastmcp FastMCP is a Python framework for building Model Context Protocol servers, clients and interactive apps. You declare a tool as an ordinary Python function and FastMCP generates the schema, validation and documentation; clients connect to any server by URL with transport, authentication and lifecycle handled. Apps give tools interactive UIs rendered inside the conversation, and there is an official TypeScript counterpart.
• Trended earlier REPO nduc99911/repo-context-mcp Repo Context MCP repo-context-mcp is a local MCP server and CLI that gives AI coding agents a repository map, fast code search and token-budgeted context packs instead of dumping whole repos into prompts.
• Trended earlier REPO punkpeye/awesome-remote-mcp-servers Awesome Remote MCP Servers A curated list of remote Model Context Protocol servers, which are hosted endpoints you connect to by URL instead of installing locally.