Max Isbey
196b9598e6
`MCPServer(token_verifier=...)` no longer needs `auth=AuthSettings(...)`. On its own a verifier is now a plain bearer gate: requests without a token it accepts get a 401 whose `WWW-Authenticate` carries no `resource_metadata`, no protected-resource metadata route is published, and `get_access_token()` works as before. `AuthSettings` keeps its job of describing that gate to OAuth clients (required scopes, RFC 9728 metadata, the discovery pointer in the 401), so it is what you add when a real authorization server issues the tokens. Previously the constructor refused a verifier without settings, which forced anyone with a pre-shared token to invent an issuer URL, and the low-level `Server.streamable_http_app(token_verifier=...)` accepted the same shape but answered every request 401, valid token included, because the authentication backend was only installed when settings were given. Both wiring sites (and `MCPServer.sse_app`) now install the backend whenever a verifier is present. The authorization docs gain a "Just a pre-shared token" section with a runnable example, and the constructor still refuses the two shapes that cannot work: settings with nothing to gate with, and an embedded authorization-server provider without settings for its issuer.
MCP Python SDK
Python implementation of the Model Context Protocol (MCP)
Note
This is v2 of the MCP Python SDK, the current stable release line. It is a major rework of the SDK, both to support the 2026-07-28 MCP specification (and every earlier revision) and to fix long-standing architectural issues. Coming from v1? See What's new in v2 for the tour of what changed and the migration guide for every breaking change.
Not ready to migrate? v1.x lives on the
v1.xbranch, continues to receive critical bug fixes and security patches, and is documented at https://py.sdk.modelcontextprotocol.io/v1/. Sincepip install mcpnow installs 2.x, keep a<2upper bound on your requirement (for examplemcp>=1.28,<2) until you've migrated.Something rough, confusing, or broken? Open an issue or find us in #python-sdk-dev on the MCP Contributors Discord.
Documentation
The documentation lives at https://py.sdk.modelcontextprotocol.io/.
It has a Get started guide, What's new in v2, the API reference, and the migration guide.
What is MCP?
The Model Context Protocol lets you build servers that expose data and functionality to LLM applications in a secure, standardized way. Think of it like a web API, but designed for LLM interactions. With this SDK you can:
- Build MCP servers that expose tools, resources, and prompts to any MCP host
- Build MCP clients that connect to any MCP server
- Speak every standard transport: stdio, Streamable HTTP, and SSE
Requirements
Python 3.10+.
Installation
uv add "mcp[cli]" # or: pip install "mcp[cli]"
The cli extra adds the mcp command-line tool (mcp dev, mcp run, mcp install) on top of the SDK; install plain mcp if you don't need it. For one-off commands, uv run --with "mcp[cli]" mcp ... works without a project.
A server in 15 lines
Create a server.py:
from mcp.server import MCPServer
mcp = MCPServer("Demo")
@mcp.tool()
def add(a: int, b: int) -> int:
"""Add two numbers."""
return a + b
@mcp.resource("greeting://{name}")
def greeting(name: str) -> str:
"""Greet someone by name."""
return f"Hello, {name}!"
Full example: docs_src/index/tutorial001.py
That's a complete MCP server: one tool, one templated resource. Open it in the MCP Inspector:
uv run mcp dev server.py
Call add with a=1, b=2 and you get 3 back.
Notice what you did not write: no JSON Schema (a: int, b: int is the schema), no request parsing, no validation code, no protocol handling. Two type-hinted Python functions and a docstring.
Get started takes it from here.
A client in 10 lines
The same package is a full MCP client. Client connects to a URL, a stdio subprocess, a custom transport, or (for tests) straight to a server object in memory with no transport at all:
import asyncio
from mcp import Client
from server import mcp
async def main() -> None:
async with Client(mcp) as client:
result = await client.call_tool("add", {"a": 1, "b": 2})
print(result.structured_content) # {'result': 3}
asyncio.run(main())
Swap mcp for "http://localhost:8000/mcp" and the exact same code talks to a remote server.
Contributing
We are passionate about supporting contributors of all levels of experience and would love to see you get involved in the project. See the contributing guide to get started.
License
This project is licensed under the MIT License. See the LICENSE file for details.