A local Model Context Protocol (MCP) server that provides structured, high-signal insight into a Git repository, enabling AI coding agents to understand project state, structure, activity, and risk — without uploading or modifying the codebase. AI coding agents (Claude Code, Cursor, Codex, Gemini, etc.) are powerful, but they lack situational awareness when working with non-trivial codebases. They
Add this skill
npx mdskills install TamiShaks-2/git-context-mcpWell-documented MCP server providing Git repository analysis tools for AI coding agents
A local Model Context Protocol (MCP) server that provides structured, high-signal insight into a Git repository, enabling AI coding agents to understand project state, structure, activity, and risk — without uploading or modifying the codebase.
Note
This README was generated usinggit-context-mcpitself, by connecting an AI assistant to the repository through the exposed MCP tools.
AI coding agents (Claude Code, Cursor, Codex, Gemini, etc.) are powerful, but they lack situational awareness when working with non-trivial codebases.
They often struggle to answer questions like:
git-context-mcp solves this by turning Git history and repository structure into explicit, machine-readable context that AI agents can consume before writing or reviewing code.
git-context-mcp is a local-first MCP server focused on development context extraction, not repository manipulation.
It exposes Git-based analysis tools that help AI coding agents quickly understand:
Snapshot of the current Git repository state.
Structured directory tree with identification of important files.
Analysis of Git history to surface frequently modified files.
High-level summary of recent development and technical debt.
Detection of large, complex, or high-churn files.
git clone https://github.com/TamiShaks-2/git-context-mcp.git
cd git-context-mcp
python -m venv .venv
source .venv/bin/activate # macOS / Linux
# or
.venv\Scripts\activate # Windows
pip install -e .
Transport Type: STDIO
Command:
/python
Arguments:
src/server.py
| Tool | Purpose |
|---|---|
| project_status | Repository state awareness |
| code_map | Structural understanding |
| recent_activity | Development churn analysis |
| work_summary | High-level progress overview |
| risk_scan | Maintenance risk detection |
All tools operate in read-only mode.
git-context-mcp/
├── src/
│ ├── tools/
│ │ ├── code_map.py
│ │ ├── git_activity.py
│ │ ├── git_ops.py
│ │ ├── project_status.py
│ │ ├── risk_scan.py
│ │ └── work_summary.py
│ └── server.py
├── tests/
├── pyproject.toml
└── README.md
pytest
MIT License
Install via CLI
npx mdskills install TamiShaks-2/git-context-mcpGit Context MCP is a free, open-source AI agent skill. A local Model Context Protocol (MCP) server that provides structured, high-signal insight into a Git repository, enabling AI coding agents to understand project state, structure, activity, and risk — without uploading or modifying the codebase. AI coding agents (Claude Code, Cursor, Codex, Gemini, etc.) are powerful, but they lack situational awareness when working with non-trivial codebases. They
Install Git Context MCP with a single command:
npx mdskills install TamiShaks-2/git-context-mcpThis downloads the skill files into your project and your AI agent picks them up automatically.
Git Context MCP works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.