The Gitingest MCP Server integrates with AI assistants via Model Context Protocol (MCP) to analyze and ingest Git repositories into a structured text format.
Repository Analysis: Analyzes repositories from URLs or local paths, providing codebase insights
Flexible Filtering: Supports filtering by file size (max_file_size), patterns (include_patterns, exclude_patterns), and specific branches
Structured Output: Returns repository summaries, file tree structures, and content in an AI-friendly format
Multiple Installation Options: Available via PyPI, GitHub, or local installation with configurable settings
Analyzes Git repositories and transforms them into structured text digests, supporting filtering by file size, patterns, and branches to help AI assistants understand codebases.
Enables ingestion of GitHub repositories, extracting repository summaries, file structures, and content to provide comprehensive codebase insights.
Supports installation through PyPI, allowing the server to be easily integrated with AI assistants via package management.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Gitingest MCP Server analyze the repository at https://github.com/example/project and give me a summary of its structure"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server implementation that integrates with gitingest for turning any Git repository into a simple text digest of its codebase.
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
Related MCP server: GitHub MCP Server
Add the following configuration to your AI assistant's settings to enable gitingest-mcp as an MCP server:
{
"mcpServers": {
"gitingestmcp": {
"command": "uvx",
"args": ["gitingestmcp@latest"]
}
}
}{
"mcpServers": {
"gitingestmcp": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/narumiruna/gitingest-mcp",
"gitingestmcp"
]
}
}
}{
"mcpServers": {
"gitingestmcp": {
"command": "uv",
"args": [
"run",
"--directory",
"/home/<user>/workspace/gitingest-mcp",
"gitingestmcp"
]
}
}
}The server provides the following tool:
ingest_gitAnalyzes a Git repository and returns its content in a structured format.
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")
A string containing:
Repository summary
Tree-like structure of the files
Content of the repository files
gitingest website: https://gitingest.com/
gitingest repository: https://github.com/cyclotruc/gitingest
See the LICENSE file for details.
This function analyzes a source (URL or local path), clones the corresponding repository (if applicable), and processes its files according to the specified query parameters. It can return a summary, a tree-like structure of the files, or the content of the files.
Inputs: source (required), branch, exclude_patterns, include_patterns, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'ingest_git' has a clearly defined purpose that is distinct by default.
A single tool inherently has perfect naming consistency. The tool name 'ingest_git' follows a clear verb_noun pattern, and there are no other tools to create inconsistency.
One tool is too few for the apparent scope of a Git ingestion server. The tool description suggests capabilities like cloning, processing files, and returning summaries, structures, or content, which could reasonably be split into multiple specialized tools (e.g., clone_repo, list_files, get_file_content). A single tool feels thin and may force agents to handle complex parameter parsing.
The tool covers basic ingestion and file access, but there are notable gaps for a Git domain. Missing operations include version control actions (e.g., commit, branch, diff), repository management (e.g., create, delete), and more granular file operations. Agents can work around this by using the single tool for all tasks, but it lacks lifecycle coverage.
A MCP server built for developers enabling Git based project management with project and personal…
