What runtime or dependencies are required?
Node.js is required. The server is installed via npm and runs as a command-line tool.
@ItamarZand88
基本情報
MCP server for GitHub Knowledge Graph exploration and analysis
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"github-knowledge-graph-mcp": {
"command": "npx",
"args": [
"github-knowledge-graph-mcp"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
The GitHub Knowledge Graph MCP Server generates and interacts with knowledge graphs of GitHub repositories using the Model Context Protocol (MCP). It enables AI models to analyze and explore code repositories through a structured graph.
Install globally with npm install -g github-knowledge-graph-mcp, then run github-kg-mcp or npx github-knowledge-graph-mcp. Configure environment variables like MCP_PORT, MCP_HOST, MCP_DATA_DIR, and MCP_LOG_LEVEL. To integrate with Claude Desktop, run npx github-knowledge-graph-mcp install-claude.
Node.js is required. The server is installed via npm and runs as a command-line tool.
By default, data is stored in `$HOME/.github-knowledge-graph/data`, configurable via `MCP_DATA_DIR`.
Run `npx github-knowledge-graph-mcp install-claude` to automatically add the server configuration to Claude Desktop.
The server uses the Model Context Protocol (MCP) over HTTP, with configurable host and port via `MCP_PORT` and `MCP_HOST`.
The README does not mention any authentication mechanism. The server binds to localhost by default.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths
コメント