MCP Python SDK

MCP Python SDK
A fast way to write an MCP server in Python.
The official library for writing MCP servers and clients in Python.
What is MCP Python SDK and who is it for?
The OPCAIOS tools library files MCP Python SDK under MCP: it is an MCP server. Short label: GitHub. The official library for writing MCP servers and clients in Python. The MCP Python SDK is the official Python library set for building both MCP servers and MCP clients. For servers, you declare tools, resources and prompts using simple decorators on Python functions with type hints; for clients, you connect to any MCP server. Best suited to: Python developers, automation teams. According to OPCAIOS, the editorial score of MCP Python SDK is 4.0 out of 5: A fast way to write an MCP server in Python.
- Platform: Python 3.10+ on macOS, Windows, Linux.
- Difficulty to get started: intermediate.
Is MCP Python SDK free, and what does it cost?
MCP Python SDK is free to use. Free, open source (MIT). Additionally, prices are set by the provider and can change, so compare with the official MCP Python SDK site before you pay. To compare costs, the MCP group of the library also includes Model Context Protocol (free), MCP Servers (free), and MCP specification (free).
What are the main features of MCP Python SDK?
According to OPCAIOS, the standout strengths of MCP Python SDK are official, MIT license, decorator-based declaration, and both server and client, among others. Additionally, the list below explains each of the 6 recorded features.
- Official, MIT license: The SDK is developed by the MCP project and licensed under MIT.
- Decorator-based declaration: Use @mcp.tool() and @mcp.resource() on Python functions to turn them into tools and data for AI.
- Both server and client: Build a server and also use the Client class to call tools on other servers.
- Three transports: Supports stdio, Streamable HTTP and SSE.
- Handy mcp command: mcp dev opens the server in the Inspector, mcp run runs the server, mcp install installs it into an app.
- Upgrade docs available: The documentation has a section introducing v2 and a migration guide.
When should you use MCP Python SDK?
MCP Python SDK is used for 5 kinds of work. When using MCP Python SDK, the most typical case is expose sales data to AI. Additionally, the main audience is python developers, automation teams.
- Expose sales data to AI: Write a Python tool that queries the order database so an AI assistant can answer revenue questions.
- Reuse existing scripts: Wrap Excel and reporting scripts as tools that employees call through AI.
- Connect internal systems: Create a server that calls your company's CRM or warehouse software APIs.
- Build your own agent: Use the Client part so your Python app can call tools from multiple MCP servers.
- Deploy a remote server: Run the server over Streamable HTTP so many people in the company can share it.
How do you get started with MCP Python SDK?
When using MCP Python SDK for the first time, you go through 5 steps, which OPCAIOS rates as intermediate difficulty. The first step is to install the SDK with uv, and the last is to run over HTTP. The steps are listed in order below.
- Install the SDK with uv. A project using uv can add the package with the CLI extra.
- Or install with pip. Use pip if you don't use uv; drop [cli] if you don't need the mcp command.
- Write a minimal server. Create server.py, initialize MCPServer and attach @mcp.tool() to a function with type hints.
- Try it in the Inspector. Open the server in the MCP Inspector to test the tool before connecting it to an AI app.
- Run over HTTP. Serve the server over Streamable HTTP; the default endpoint in the README is localhost:8000/mcp.
What is MCP Python SDK?
The MCP Python SDK is the official Python library set for building both MCP servers and MCP clients. For servers, you declare tools, resources and prompts using simple decorators on Python functions with type hints; for clients, you connect to any MCP server.
The SDK requires Python 3.10 or later and supports the stdio, Streamable HTTP and SSE transports. The package with the cli extra provides the mcp command to run a server, open the MCP Inspector or install a server into an AI app.
It is a good fit for businesses that already have Python scripts, data systems or Python automation and want to expose them to AI assistants.
How much does MCP Python SDK cost?
Free, open source (MIT)
Prices are set by the provider and can change; check the official site for the latest.
Key features of MCP Python SDK
Official, MIT license
The SDK is developed by the MCP project and licensed under MIT.
Decorator-based declaration
Use @mcp.tool() and @mcp.resource() on Python functions to turn them into tools and data for AI.
Both server and client
Build a server and also use the Client class to call tools on other servers.
Three transports
Supports stdio, Streamable HTTP and SSE.
Handy mcp command
mcp dev opens the server in the Inspector, mcp run runs the server, mcp install installs it into an app.
Upgrade docs available
The documentation has a section introducing v2 and a migration guide.
What is MCP Python SDK used for?
Expose sales data to AI
Write a Python tool that queries the order database so an AI assistant can answer revenue questions.
Reuse existing scripts
Wrap Excel and reporting scripts as tools that employees call through AI.
Connect internal systems
Create a server that calls your company's CRM or warehouse software APIs.
Build your own agent
Use the Client part so your Python app can call tools from multiple MCP servers.
Deploy a remote server
Run the server over Streamable HTTP so many people in the company can share it.
How to use MCP Python SDK
- 1
Install the SDK with uv
A project using uv can add the package with the CLI extra.
$uv add "mcp[cli]" - 2
Or install with pip
Use pip if you don't use uv; drop [cli] if you don't need the mcp command.
$pip install "mcp[cli]" - 3
Write a minimal server
Create server.py, initialize MCPServer and attach @mcp.tool() to a function with type hints.
- 4
Try it in the Inspector
Open the server in the MCP Inspector to test the tool before connecting it to an AI app.
$uv run mcp dev server.py - 5
Run over HTTP
Serve the server over Streamable HTTP; the default endpoint in the README is localhost:8000/mcp.
$uv run mcp run server.py --transport streamable-http
MCP Python SDK video guides
Intro to MCP Servers – Model Context Protocol with Python Course
freeCodeCamp.org
Build Anything With a CUSTOM MCP Server - Python Tutorial
Tech With Tim
Python + MCP: Building MCP servers with FastMCP
Microsoft Reactor
Real-world example: MCP Python SDK
A cosmetics store chain in Ho Chi Minh City already has a Python script that totals revenue by branch. A developer wraps that function as a tool with the MCP Python SDK, tests it in the Inspector, then runs the server over Streamable HTTP on an internal machine. A regional manager asks the AI assistant about last week's branch revenue and the AI calls the existing function instead of staff running it by hand.
Tips for using MCP Python SDK
Write full type hints
The SDK relies on function types to describe parameters to the AI.
Name and describe tools clearly
A good description helps the model pick the right tool.
Always test with mcp dev
Check the tool in the Inspector before handing it to users.
Check the v2 docs
If you follow older guides, compare against the migration page since examples now use MCPServer.
MCP Python SDK: frequently asked questions
Which Python version is needed?
Python 3.10 or later.
Is the [cli] extra required?
No. You only need it if you want the mcp commands such as mcp dev, mcp run, mcp install.
Is the SDK free?
Yes, open source under the MIT license.
Can I build a client?
Yes, the SDK provides a Client class to connect to and call tools on HTTP or stdio servers.
Useful links
Want to apply this in your business?
OPCAIOS looks at your workflows, picks the right tools and sets them up with your team. The first call is free.
