GitInsight-MCP

Exposes GitHub profile data via MCP so AI assistants can query repos, commits, stats, and portfolio insights.
  • typescript

2

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "marwaniiwael18-gitinsight-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/GitInsight-MCP/dist/index.js"
      ],
      "env": {
        "GITHUB_TOKEN": "your_github_token_here",
        "GITHUB_USERNAME": "marwaniiwael18",
        "CACHE_TTL_SECONDS": "3600",
        "CACHE_CHECK_PERIOD_SECONDS": "600"
      }
    }
  }
}

You run a dedicated MCP Server that exposes your GitHub profile data to AI assistants. It lets Claude or other MCP clients query repositories, commits, statistics, and generate recruiter-friendly insights, all while handling caching and rate limits for GitHub data.

How to use

Use an MCP client to connect to the GitInsight-MCP server. The server speaks the MCP protocol and provides tools you can call to fetch and analyze your GitHub profile data. After you configure the client, you can ask questions like about your most starred repositories, overall statistics, contribution activity, and recruiter-focused outputs such as skills matrices and portfolio summaries. The server handles caching and rate limits so you get fast, reliable results.

How to install

# Prerequisites
node -v  # should be 18+
npm -v    # or yarn -v

# Clone the project
git clone https://github.com/marwaniiwael18/GitInsight-MCP.git
cd GitInsight-MCP

# Install dependencies
npm install

# Build the project
npm run build

# Start the server (standalone)
npm start

Configuration

Prepare an environment file with GitHub authentication details and cache settings. You provide your GitHub token and username so the server can access GitHub data on your behalf and cache results to improve performance.

# GitHub Personal Access Token
GITHUB_TOKEN=ghp_your_actual_token_here

# Your GitHub Username
GITHUB_USERNAME=marwaniiwael18

# Cache Settings (optional)
CACHE_TTL_SECONDS=3600
CACHE_CHECK_PERIOD_SECONDS=600

Security and runtime notes

Use token-based authentication and keep tokens secret. The server uses the token to fetch data from GitHub and caches results to respect rate limits. If you trouble with rate limits, enable caching and ensure you provide a valid token.

Troubleshooting

Common issues include missing environment variables, GitHub API rate limits, and token problems. Ensure your .env file contains GITHUB_TOKEN and GITHUB_USERNAME. If you hit rate limits, rely on the cache and provide a valid token to increase allowances. If Claude Desktop does not detect the server, verify absolute paths in your client configuration and restart the client.

Development tips

For development workflows, you can build, run in development mode, and test with MCP Inspector to verify tool behavior before using with an MCP client.

Available tools

list_repositories

Return the user's public repositories with metadata such as name, description, stars, forks, language, and topics.

get_repository_details

Fetch comprehensive details for a specific repository, including topics and optional README content.

get_recent_commits

Retrieve recent commits for a repository or all repositories with metadata like SHA, message, author, and date.

get_repository_stats

Compute aggregate statistics across all repositories, such as counts, language breakdown, and top repos.

search_projects_by_tech

Filter repositories by language and topic with sorting and limits.

get_contribution_activity

Analyze contribution activity, including total commits, active days, and streaks.

get_skills_matrix

Generate a comprehensive technical skills assessment matrix for recruiters.

generate_portfolio_summary

Create a recruiter-friendly portfolio summary including profile, achievements, and technologies.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational