Docs MCP Server

🚀 MCP Server Example

This repository contains a code example implementing a Model Context Protocol (MCP) server for the latest documentation. It demonstrates how to build a functional MCP server for integration with various Large Language Model (LLM) clients.

🚀 Quick Start

Install the uv Package Manager

On MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

On Windows:

pip install uv

After installation, restart your terminal to ensure the uv command works.

Project Setup

1. Clone and initialize the project:

# Create a new directory for our project
git clone https://github.com/wolderufael/docs-MCP-server.git
cd docs-mcp-server

# Create a virtual environment and activate it
uv venv
source .venv/bin/activate  # On Windows, use: .venv\Scripts\activate

2. Install dependencies:

uv venv sync 

Run the Server

1. Start the MCP server:

uv run main.py

2. The server will accept connections after startup.

✨ Features

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of it as the USB-C port in AI applications—it offers a standard way for AI models to connect to different data sources and service tools.

Core Advantages

• A growing list of pre-built integrations allowing direct connection of your LLM.
• Flexibility to switch between different LLM providers and vendors.
• Best practices for protecting data within the infrastructure.

Architecture Overview

MCP uses a client-server architecture where host applications can connect to multiple servers:

• MCP Host: Programs like Claude Desktop, IDEs, or AI tools that want to access data via MCP.
• MCP Client: A protocol client maintaining a one-to-one connection with the server.
• MCP Server: A standard lightweight program providing specific functions.
• Data Source: Can be local (files, databases) or remote services (APIs), which the MCP server can access.

Core MCP Concepts

MCP servers can provide three main types of functionality:

• Resources: Readable data similar to files (e.g., API responses or file contents).
• Tools: Functions that LLMs can call (with user approval).
• Prompts: Pre-written templates to assist users in completing specific tasks.

📦 Installation

System Requirements

• Python 3.10 or higher.
• MCP SDK 1.2.0 or higher.
• uv package manager.

💻 Usage Examples

Connect to Cursor AI

1. Install Cursor AI from the official website.
2. Configure Cursor to use your MCP server: Edit the .cursor\mcp.json file:

{
  "mcpServers": {
    "mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/YOUR/mcp-server",
        "run",
        "main.py"
      ]
    }
  }
}

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.