What API key and bundle do I need?
You need a Toolhouse API key (free to get started) and a bundle name from your Toolhouse dashboard. The bundle groups the tools you want to use on your client.
@toolhouse-community
基本情報
概要はまだありません
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": {
"mcp-server-toolhouse": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"uv",
"--directory",
"/path/to/toolhouse_mcp",
"run",
"toolhouse-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。
This MCP server connects MCP clients with Toolhouse's tools, built on Toolhouse and Groq's API for fast inference. It allows developers using compatible MCP clients (e.g., Claude Desktop) to access a library of tools from the Toolhouse platform.
Set the environment variables TOOLHOUSE_API_KEY and TOOLHOUSE_BUNDLE_NAME, then add the server to your MCP client's configuration (e.g., claude_desktop_config.json). Run via uvx mcp_server_toolhouse with the two env vars, or clone the repository and use uv pointing to the local directory.
You need a Toolhouse API key (free to get started) and a bundle name from your Toolhouse dashboard. The bundle groups the tools you want to use on your client.
The server is designed for any MCP client; the README specifically mentions Claude Desktop, Cursor, Windsurf, and Cline.
Use the MCP Inspector via `npx @modelcontextprotocol/inspector uv --directory /path/to/toolhouse_mcp run toolhouse-mcp`. MCP servers run over stdio, so the Inspector helps with debugging.
The server can run with `uvx` (no local install) or locally with `uv` after cloning the repository. It is a Python package (`mcp_server_toolhouse`), so Python and `uv` are required.
The Toolhouse API key and bundle are passed as environment variables. Data flows through the Toolhouse platform according to your bundle settings; no data is stored by this MCP server itself.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
コメント