MCP Python SDK Documentation
Read the docs Documentation for the MIT decentralized AI, MCP hackathon
aidecentralized
README
MCP Python SDK Documentation
This repository contains the documentation for the Model Context Protocol (MCP) Python SDK. It is built using Sphinx and the Read the Docs theme.
Overview
The Model Context Protocol (MCP) is an open standard that defines how applications interact with large language models (LLMs). This documentation aims to help developers:
- Understand the core concepts of MCP
- Build MCP servers to expose resources, tools, and prompts
- Create MCP clients to connect to MCP servers
- Explore advanced topics and best practices
FastMCP
Our documentation includes comprehensive coverage of FastMCP, a high-level, Pythonic interface for building MCP servers. Originally a standalone project, FastMCP has been integrated into the official MCP Python SDK. It provides a developer-friendly way to create MCP servers with minimal boilerplate:
from mcp.server.fastmcp import FastMCP
mcp = FastMCP("Demo 🚀")
@mcp.tool()
def add(a: int, b: int) -> int:
"""Add two numbers"""
return a + b
The SDK provides multiple ways to run your server:
- Development mode with the MCP Inspector
- Claude Desktop integration
- Direct execution for custom deployments
Building the Documentation
-
Install Dependencies
First, make sure you have Python installed. Then, install the required packages:
# Using conda (recommended) conda activate cuda_test pip install -r requirements.txt # Or using pip in a virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt
-
Build the Documentation
To build the documentation:
make html
The built documentation will be in the
_build/html/
directory. -
Live Preview
For a live preview with auto-reload:
sphinx-autobuild . _build/html
Then open your browser to http://localhost:8000.
Hosting on GitHub Pages
You can host this documentation on GitHub Pages by following these steps:
-
Create a GitHub Repository
# Initialize a local repository if you haven't already git init git add . git commit -m "Initial commit with MCP documentation" # Create a repository on GitHub through the web interface # Then add the remote and push git remote add origin https://github.com/yourusername/mcp_docs.git git push -u origin main
-
Set Up GitHub Pages
There are two ways to set up GitHub Pages for your documentation:
Option 1: Using GitHub Actions (Recommended)
The repository already includes a GitHub Actions workflow at
.github/workflows/docs.yml
that will automatically build and deploy the documentation to GitHub Pages whenever you push to the main branch.- Go to your GitHub repository
- Navigate to "Settings" > "Pages"
- Under "Source", select "GitHub Actions"
- Make sure the "GitHub Actions" workflow is running after your first push
Option 2: Manual Setup with gh-pages Branch
If you prefer to manage the deployment manually:
# Create an orphan gh-pages branch git checkout --orphan gh-pages git rm -rf . touch .nojekyll git add .nojekyll git commit -m "Initial gh-pages commit" git push origin gh-pages git checkout main # Build and copy the documentation to gh-pages make html git checkout gh-pages cp -r _build/html/* . git add . git commit -m "Update documentation" git push origin gh-pages git checkout main
Then go to your GitHub repository's Settings > Pages and select the gh-pages branch as the source.
-
Access Your Documentation
Your documentation will be available at:
https://yourusername.github.io/mcp_docs/
-
Update the Documentation
Whenever you want to update the documentation:
# If using GitHub Actions # Just push your changes to the main branch git add . git commit -m "Update documentation" git push origin main # If using manual gh-pages setup make html git checkout gh-pages cp -r _build/html/* . git add . git commit -m "Update documentation" git push origin gh-pages git checkout main
Documentation Structure
index.rst
: Main entry pointintroduction.rst
: Introduction to MCPgetting-started.rst
: Getting started guideserver-guide.rst
: Guide for building MCP serversclient-guide.rst
: Guide for building MCP clientsexamples.rst
: Example MCP applicationsadvanced-topics.rst
: Advanced MCP conceptsapi-reference.rst
: API reference
Contributing
Contributions to improve the documentation are welcome! Here's how you can contribute:
- Fork the repository
- Create a new branch for your changes
- Make your changes
- Build the documentation to verify your changes
- Submit a pull request
Resources
- Official MCP Website
- MCP Python SDK GitHub
- MCP Specification
- Officially Supported Servers
- GitHub Discussions
- FastMCP GitHub (Legacy)
License
This documentation is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.