mcpField
G
Gitingest MCP Server

Gitingest MCP Server

Local
github.com/narumirunaVersion Control12Updated 18w ago
Repository

About Gitingest MCP Server

Gitingest MCP Server exposes Git repository ingestion to MCP-compatible AI assistants. It returns a structured digest with repository details, file layout, and content, with options to filter files and select a branch.

Key features

  1. 01Ingest remote repositories or local directories
  2. 02Filter by file size and patterns
  3. 03Select a branch for analysis
  4. 04Return summary, file tree, and content

Use cases

  1. 01Prepare a repository digest for AI-assisted analysis
  2. 02Limit ingestion to selected files or folders
  3. 03Analyze a specific repository branch

MCP support

The MCP server provides the `ingest_git` tool, which analyzes a Git URL or local directory and returns repository information and file content.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gitingest": {
      "command": "uvx",
      "args": [
        "gitingestmcp@latest"
      ]
    }
  }
}
Run commanduvx gitingestmcp@latest

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypigitingestmcp@latest

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Gitingest MCP Server

A Model Context Protocol (MCP) server implementation that integrates with gitingest for turning any Git repository into a simple text digest of its codebase.

Gitingest Server MCP server

Features

  • Easy integration with AI assistants through the Model Context Protocol
  • Git repository analysis and ingestion capabilities
  • Support for filtering files by size, patterns, and branches
  • Returns comprehensive repository information including summaries, file structure, and content

Usage

Configuration Options

Add the following configuration to your AI assistant's settings to enable gitingest-mcp as an MCP server:

PyPI Installation
{
  "mcpServers": {
    "gitingestmcp": {
      "command": "uvx",
      "args": ["gitingestmcp@latest"]
    }
  }
}
GitHub Installation
{
  "mcpServers": {
    "gitingestmcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/narumiruna/gitingest-mcp",
        "gitingestmcp"
      ]
    }
  }
}
Local Installation
{
  "mcpServers": {
    "gitingestmcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/home/<user>/workspace/gitingest-mcp",
        "gitingestmcp"
      ]
    }
  }
}

API

The server provides the following tool:

ingest_git

Analyzes a Git repository and returns its content in a structured format.

Parameters:
  • source: The URL of a Git repository or a local directory path
  • max_file_size (optional): Maximum allowed file size in bytes (default: 10MB)
  • include_patterns (optional): Pattern or set of patterns specifying files to include (e.g., "*.md, src/")
  • exclude_patterns (optional): Pattern or set of patterns specifying files to exclude
  • branch (optional): The branch to clone and analyze (default: "main")
Returns:

A string containing:

  1. Repository summary
  2. Tree-like structure of the files
  3. Content of the repository files

Resources

License

See the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.