What does GitHub Chat MCP do?
It provides two main tools: Repository Indexing (index and analyze a GitHub repository) and Repository Querying (ask questions about the indexed repository). It uses the GitHub Chat API.
@AsyncFuncAI
基本情報
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
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-chat-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"github-chat-mcp",
"--client",
"claude"
]
}
}
}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。
GitHub Chat MCP is a Model Context Protocol server that analyzes and queries GitHub repositories using the GitHub Chat API. It is intended for developers who want to ask questions about a repository’s codebase through an AI assistant.
Install via pip install github-chat-mcp or uv install github-chat-mcp, then configure it in your MCP client (e.g., Cursor, Claude Desktop) using the command uvx github-chat-mcp. First index a repository (e.g., “Index the GitHub repository at https://github.com/username/repo”), then ask questions about it (e.g., “What is the core tech stack used in this repository?”).
It provides two main tools: Repository Indexing (index and analyze a GitHub repository) and Repository Querying (ask questions about the indexed repository). It uses the GitHub Chat API.
Yes, a GitHub Chat API key is required to use the service. However, for the freemium release, no environment variables are needed in the configuration.
Python, pip or uv package manager, and the GitHub Chat API key. On macOS/Linux, `curl` is used to install uv; on Windows, a PowerShell command is provided.
The server communicates with the GitHub Chat API over the network. No data is stored locally beyond temporary indexing state in the MCP session.
The server uses standard MCP transport (stdin/stdout) as is typical for local MCP servers. Authentication is handled via environment variables when required.

Instant blogs for AI agents: a publishing CMS with no dashboard. One signup call returns a blog, an API key and a live URL; then publish markdown posts and get public URLs back.
Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

Search a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
コメント