What dependencies or runtime does Hackage Documentation MCP require?
Python 3.7+ and the packages `httpx`, `beautifulsoup4`, and `fastmcp`.
@apenugon
基本情報
An MCP server to give Claude easy access to pulling docs
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": {
"haskell-hackage-mcp": {
"command": "python",
"args": [
"main.py"
]
}
}
}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。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Hackage Documentation MCP is a Machine-Controlled Program (MCP) server that provides AI assistants with real‑time access to Haskell documentation from Hackage. It enables AI models to retrieve precise, up‑to‑date documentation for specific Haskell modules, improving the AI’s ability to assist with Haskell programming despite limited training data in this domain.
Install Python 3.7+, then pip install httpx beautifulsoup4 fastmcp. Run python main.py to start the server with stdio transport. Use any MCP‑compatible AI assistant to call the tool get_docs(package, version, module) with a Hackage package name, exact version string, and module name (e.g., get_docs("lens", "5.0.0", "Control.Lens")).
Python 3.7+ and the packages `httpx`, `beautifulsoup4`, and `fastmcp`.
Call `get_docs(package, version, module)` – for example, `get_docs("vector-algorithms", "0.8.0", "Data.Vector.Algorithms")`.
Yes, it requires an internet connection to access documentation from Hackage.
It only provides documentation content, not implementation code. Documentation quality varies between Haskell packages, and an internet connection is required.
Yes, any package name, version, and module that exist on Hackage can be queried. An error message is returned if retrieval fails.

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.
Project context your AI can query through MCP — with source evidence.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
コメント