GitHub Chat MCP server

GitHub Chat MCP is a server that allows AI assistants to analyze and query GitHub repositories using the GitHub Chat API. With this tool, you can index GitHub repositories and ask detailed questions about their code, architecture, and implementation details.

Installation

You can install the GitHub Chat MCP server using either pip or the uv package manager:

# Install with pip
pip install github-chat-mcp

# Or install with the newer uv package manager
uv install github-chat-mcp

If you don't have uv installed, you can install it first:

For MacOS/Linux:

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

For Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Setup with AI Assistants

Setup with Cursor (Recommended)

Create an mcp.json file with the following content:

{
  "mcpServers": {
    "github-chat": {
      "command": "uvx",
      "args": [
        "github-chat-mcp"
      ]
    }
  }
}

Setup with Claude Desktop

Add the following to your Claude Desktop configuration file:

{
  "mcpServers": {
    "github-chat": {
      "command": "uvx",
      "args": ["github-chat-mcp"],
      "env": {
      }
    }
  }
}

You can find the config file location through: Hamburger Menu -> File -> Settings -> Developer -> Edit Config

Installing via Smithery

You can also install GitHub Chat for Claude Desktop automatically using Smithery:

npx -y @smithery/cli install github-chat-mcp --client claude

Using GitHub Chat

Once installed, you can use GitHub Chat with your AI assistant:

1. Index a GitHub repository first:

   • Example prompt: "Index the GitHub repository at https://github.com/username/repo"

2. Then ask questions about the repository:

   • Example prompt: "What is the core tech stack used in this repository?"

Other example prompts:

• "Use github-chat-mcp to analyze the React repository"
• "Index the TypeScript repository with github-chat-mcp and ask about its architecture"

Debugging

If you encounter issues, you can run the following to debug:

npx @modelcontextprotocol/inspector uvx github-chat-mcp

You can adjust the logging level through the FASTMCP_LOG_LEVEL environment variable:

FASTMCP_LOG_LEVEL="ERROR" uvx github-chat-mcp

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.