GitHub Repository Explorer MCP server

Extracts and provides GitHub repository information including summaries, directory structures, and file contents for seamless code analysis and reference during conversations.
Back to servers
Provider
Purav Parab
Release date
Mar 12, 2025
Language
Python
Stats
70 stars

This MCP server for gitingest allows you to quickly extract information about GitHub repositories, including repository summaries, project directory structures, and file content through MCP clients like Claude Desktop, Cline, Cursor, and others.

Installation Options

You can install the Gitingest-MCP server using one of the following methods.

Installing via Smithery

The easiest way to install Gitingest-MCP is using Smithery. Choose the command based on your preferred MCP client:

For Claude:

npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client claude --config "{}"

For Cursor:

npx -y @smithery/cli@latest run @puravparab/gitingest-mcp --client cursor --config "{}"

For Windsurf:

npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client windsurf --config "{}"

For Cline:

npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client cline --config "{}"

Install via GitHub

To install directly from GitHub, add the following to your MCP client config file:

{
    "mcpServers": {
        "gitingest-mcp": {
            "command": "<path to uv>/uvx",
            "args": [
                "--from",
                "git+https://github.com/puravparab/gitingest-mcp",
                "gitingest-mcp"
            ]
        }
    }
}

Installing Repo Manually

If you prefer to install the repository manually, follow these steps:

  1. Clone the repository:

    git clone https://https://github.com/puravparab/Gitingest-MCP
    cd Gitingest-MCP
    
  2. Install dependencies:

    uv sync
    
  3. Add this configuration to your MCP client config file:

    {
        "mcpServers": {
            "gitingest": {
                "command": "<path to uv>/uv",
                "args": [
                    "run",
                    "--with",
                    "mcp[cli]",
                    "--with-editable",
                    "<path to gitingest-mcp project>/gitingest_mcp",
                    "mcp",
                    "run",
                    "<path to gitingest-mcp project>/gitingest-mcp/src/gitingest_mcp/server.py"
                ]
            }
        }
    }
    

Configuring Claude Desktop

To update the Claude Desktop configuration:

  1. Open the config file in your preferred IDE:

    cursor ~/Library/Application\ Support/Claude/claude_desktop_config.json
    

    Or:

    code ~/Library/Application\ Support/Claude/claude_desktop_config.json
    

Debugging

To debug the MCP server, you can use the MCP inspector:

uv run mcp dev src/gitingest_mcp/server.py

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.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later