Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for GitHub repository ingestion
Gitingest-MCP exposes Gitingest through the Model Context Protocol so agents can fetch useful context from GitHub repositories. It surfaces repository summaries, directory structure, and file contents for client apps like Cursor and Windsurf.
Builders who want their agent to inspect GitHub repositories and pull context on demand.
You can give your agent repository context without copying files by hand.
What it does
Repository summaries
Returns a compact summary of a GitHub repository.
Directory structure
Shows the project tree so an agent can understand the layout quickly.
File content retrieval
Lets the client read file contents from a repo through the MCP server.
MCP client support
Works with MCP clients such as Claude Desktop, Cursor, Cline, and Windsurf.
Smithery install path
Can be installed through Smithery with the commands listed in the README.
How to get it
- 1To install gitingest-mcp via Smithery
npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client claude --config "{}" # Claude - 2Run
npx -y @smithery/cli@latest run @puravparab/gitingest-mcp --client cursor --config "{}" # Cursor - 3Run
npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client windsurf --config "{}" # Windsurf - 4Run
npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client cline --config "{}" # Cline - 5Clone the repo
git clone https://https://github.com/puravparab/Gitingest-MCP cd Gitingest-MCP
- 6Install dependencies
uv sync
README
Gitingest-MCP 
An MCP server for gitingest. This allows MCP clients like Claude Desktop, Cline, Cursor, etc to quickly extract information about Github repositories including
- Repository summaries
- Project directory structure
- File content
https://github.com/user-attachments/assets/c1fa596b-a70b-4d37-91d9-ea5e80284793
Table of Contents
Installation
Installing via Smithery
-
To install gitingest-mcp via Smithery:
npx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client claude --config "{}" # Claudenpx -y @smithery/cli@latest run @puravparab/gitingest-mcp --client cursor --config "{}" # Cursornpx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client windsurf --config "{}" # Windsurfnpx -y @smithery/cli@latest install @puravparab/gitingest-mcp --client cline --config "{}" # Cline
Install via Github
-
Add this to the 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
-
Clone the repo
git clone https://https://github.com/puravparab/Gitingest-MCP cd Gitingest-MCP -
Install dependencies
uv sync -
Add this to the 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" ] } } } -
If you have issues, follow this MCP server documentation
Updating the MCP client configuration
-
Add to Claude Desktop
Open config file in your IDE
cursor ~/Library/Application\ Support/Claude/claude_desktop_config.jsoncode ~/Library/Application\ Support/Claude/claude_desktop_config.json
Debug
- Using mcp inspector
uv run mcp dev src/gitingest_mcp/server.py
Files in the repo
- src
- .gitignore
- .python-version
- Dockerfile
- LICENSE
- pyproject.toml
- README.md
- smithery.yaml
- uv.lock
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.