Gitingest Mcp
@deadraid
About Gitingest Mcp
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"gitingest-mcp": {
"command": "npx",
"args": [
"-y",
"gitingest-mcp-server"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Gitingest Mcp?
Gitingest Mcp is a Model Context Protocol (MCP) server that converts Git repositories—local or remote—into compact, prompt-ready text digests for large-language models. It exposes an ingest_repository tool over stdio, allowing any MCP‑aware editor or tool to request an up‑to‑date representation of a repository.
How to use Gitingest Mcp?
Install the server via npx -y gitingest-mcp-server and add a configuration snippet to your MCP client’s mcpServers object. Then call the ingest_repository tool with a repository URL, local path, or shorthand (e.g., user/repo), plus optional parameters like branch, exclude patterns, or size limits.
Key features of Gitingest Mcp
- Works with GitHub, GitLab, Bitbucket, generic git, or a local path.
- Supports shallow cloning, sparse checkout, and submodule recursion.
- Honors both
.gitignoreand custom.gitingestignorefiles. - Powerful include/exclude glob patterns for filtering files.
- Hard limits for file size, file count, total size, and token budget.
- Built‑in retry and timeout logic for flaky networks.
Use cases of Gitingest Mcp
- Converting a codebase into a digest for conversational code understanding.
- Preparing a repository snapshot for LLM‑powered code review.
- Feeding a condensed repository representation into a Retrieval‑Augmented Generation (RAG) pipeline.
FAQ from Gitingest Mcp
What does the tool return?
It returns a single text document containing a summary (branch, commit, size, token count), a human‑readable directory tree, and the concatenated contents of every included file.
Which Git hosting services are supported?
GitHub, GitLab, Bitbucket, generic Git remotes, and local file paths are all supported. The server automatically detects the provider or lets you force one with the source parameter.
How do I filter which files are included?
You can use .gitignore and .gitingestignore files, plus additional excludePatterns and includePatterns globs. By default .gitignore is respected, and you can opt to include git‑ignored files via includeGitignored.
Are there any built‑in size or token limits?
Yes. You can set maxFileSize, maxFiles (default 1000), maxTotalSize (default 50 MiB), and maxTokens to trim the output. The server also enforces retry and timeout settings for network operations.
Can I access private repositories?
Yes. Pass an authentication token via the token parameter (e.g., a GitHub personal access token) to clone private repositories. The server uses it during the clone or fetch steps.
Frequently asked questions
What does the tool return?
It returns a single text document containing a summary (branch, commit, size, token count), a human‑readable directory tree, and the concatenated contents of every included file.
Which Git hosting services are supported?
GitHub, GitLab, Bitbucket, generic Git remotes, and local file paths are all supported. The server automatically detects the provider or lets you force one with the `source` parameter.
How do I filter which files are included?
You can use `.gitignore` and `.gitingestignore` files, plus additional `excludePatterns` and `includePatterns` globs. By default `.gitignore` is respected, and you can opt to include git‑ignored files via `includeGitignored`.
Are there any built‑in size or token limits?
Yes. You can set `maxFileSize`, `maxFiles` (default 1000), `maxTotalSize` (default 50 MiB), and `maxTokens` to trim the output. The server also enforces retry and timeout settings for network operations.
Can I access private repositories?
Yes. Pass an authentication token via the `token` parameter (e.g., a GitHub personal access token) to clone private repositories. The server uses it during the clone or fetch steps.
Basic information
More Other MCP servers
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
ghidraMCP
LaurieWiredMCP Server for Ghidra
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
Comments