MCP Git Ingest
Helps AI read GitHub repository structure and important files. Want to quickly understand what a repo is about? Prompt it with 'read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works'.
What is MCP Git Ingest?
MCP Git Ingest is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to helps ai read github repository structure and important files. want to quickly understand what a repo is about? prompt it with 'read https://github.com/adhikasp/mcp-git-ingest and determine how the co...
Helps AI read GitHub repository structure and important files. Want to quickly understand what a repo is about? Prompt it with 'read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works'.
This server falls under the Version Control category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Helps AI read GitHub repository structure and important file
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-git-ingestConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Git Ingest
MCP Git Ingest is a Python-based MCP server that gives AI assistants the ability to read and analyze GitHub repositories on demand. It exposes two tools: one that returns a visual directory tree of any public repository, and another that reads the contents of specified files from that repository. This makes it easy to point an AI at any GitHub repo and ask questions about how the code works, what the project structure looks like, or what a particular file contains — without manually copying and pasting code.
Prerequisites
- Python 3.8 or higher
- uv or uvx package manager (https://github.com/astral-sh/uv)
- Git installed and accessible on the PATH (for cloning repositories)
- Claude for Desktop or another MCP-compatible client
- Internet access to clone public GitHub repositories
Install via uvx (no manual clone required)
The server can be installed and run directly using uvx, which pulls the package from the GitHub repository. No local clone is needed.
uvx --from git+https://github.com/adhikasp/mcp-git-ingest mcp-git-ingestAdd the server to Claude Desktop configuration
Edit your claude_desktop_config.json to register mcp-git-ingest. The server uses uvx to fetch and run the latest version from GitHub automatically.
{
"mcpServers": {
"mcp-git-ingest": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/adhikasp/mcp-git-ingest",
"mcp-git-ingest"
]
}
}
}Restart Claude Desktop
Close and reopen Claude for Desktop so it reads the updated configuration and starts the mcp-git-ingest server subprocess.
Try it: fetch a repository tree
Ask Claude to retrieve the directory structure of any public GitHub repository using the github_directory_structure tool.
Read specific files from a repository
Ask Claude to read particular files from a repository using the github_read_important_files tool. You can specify multiple file paths in a single request.
MCP Git Ingest Examples
Client configuration
Full claude_desktop_config.json entry for mcp-git-ingest using uvx for zero-install setup.
{
"mcpServers": {
"mcp-git-ingest": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/adhikasp/mcp-git-ingest",
"mcp-git-ingest"
]
}
}
}Prompts to try
Prompts that use the github_directory_structure and github_read_important_files tools exposed by mcp-git-ingest.
- "Read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works"
- "Show me the directory structure of https://github.com/fastapi/fastapi"
- "Read the README.md and pyproject.toml from https://github.com/tiangolo/sqlmodel"
- "Explain the architecture of https://github.com/pydantic/pydantic by reading its source structure"
- "What does the main entry point of https://github.com/pallets/flask do?"Troubleshooting MCP Git Ingest
uvx fails with 'command not found' or cannot install the package
Install uv first by running 'curl -LsSf https://astral.sh/uv/install.sh | sh' on macOS/Linux, or 'powershell -c "irm https://astral.sh/uv/install.ps1 | iex"' on Windows. After installation, open a new terminal so the PATH is updated, then retry the uvx command.
Private or organization GitHub repositories fail to clone
The server clones repositories using public Git access. Private repositories will fail because no authentication is configured. For private repos, clone them manually to a local path and use a local filesystem MCP server instead.
Large repositories are slow to analyze or time out
The server clones the full repository on each new request and caches the clone in a temporary directory based on the URL hash. Subsequent calls to the same repo reuse the cache. For very large repositories, consider specifying only the files you need in github_read_important_files rather than fetching the entire tree first.
Frequently Asked Questions about MCP Git Ingest
What is MCP Git Ingest?
MCP Git Ingest is a Model Context Protocol (MCP) server that helps ai read github repository structure and important files. want to quickly understand what a repo is about? prompt it with 'read https://github.com/adhikasp/mcp-git-ingest and determine how the code technically works'. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Git Ingest?
Follow the installation instructions on the MCP Git Ingest GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Git Ingest?
MCP Git Ingest works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Git Ingest free to use?
Yes, MCP Git Ingest is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Git Ingest Alternatives — Similar Version Control Servers
Looking for alternatives to MCP Git Ingest? Here are other popular version control servers you can use with Claude, Cursor, and VS Code.
Ruiyu MA
★ 30.1kConnect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
GitMCP
★ 8.1kTransforms any GitHub repository or GitHub Pages site into a documentation hub for AI assistants using the Model Context Protocol. It allows AI tools to access real-time code and documentation to prevent hallucinations and provide accurate API usage
GitHub Codemunch
★ 1.8kA token-efficient MCP server for exploring GitHub repositories using tree-sitter AST parsing to extract symbol signatures and summaries. It enables users to search and retrieve specific code components while significantly reducing token consumption c
Azure DevOps MCP Server
★ 1.7kThis server provides a convenient API for interacting with Azure DevOps services, enabling AI assistants and other tools to manage work items, code repositories, boards, sprints, and more. Built with the Model Context Protocol, it provides a standard
GitHub Official
★ 1.2kOfficial GitHub integration with comprehensive API coverage
Azure DevOps
★ 367Enables interaction with Azure DevOps through Cursor chat, providing tools to manage builds, pipelines, work items, sprints, and board operations. Supports secure authentication via Personal Access Tokens and allows natural language-driven DevOps tas
Browse More Version Control MCP Servers
Explore all version control servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Git Ingest in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Git Ingest?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.