MCP Server Toolhouse

🚀 Toolhouse MCP Server

This MCP server allows you to connect MCP clients with Toolhouse's tools. Built on top of Toolhouse and Groq's API for fast inference.

Model Context Protocol (MCP) is an open protocol that enables seamless integration of LLM applications with external data sources and tools. Whether you're building an AI-driven IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with their required context.

✨ Features

• Allows compatible MCP clients (e.g., Claude desktop application) to access Toolhouse's extensive tools to enhance their functionality.

📦 Installation

Set Environment Variables

1. Toolhouse API Key: You need a Toolhouse API key to access the Toolhouse platform.

   • Sign up and create an account on Toolhouse, which is FREE to start.
   • Retrieve your API key from the Toolhouse dashboard.

2. Toolhouse Tool Bundle: You need to create a tool bundle, which is essentially a set of tools assembled from the available tools on the Toolhouse platform.

   • Navigate to Toolhouse Tool Bundles and create a tool bundle, e.g., mcp-toolhouse.
   • Add the tools you want to use on the client side, such as web scraping, memory, sending emails.
   • Ensure your tool bundle looks good (it saves automatically).

3. (Optional) Set these environment variables if you don't want to include them in the configuration:

   export TOOLHOUSE_API_KEY="your_toolhouse_api_key"
   export TOOLHOUSE_BUNDLE="your_bundle_name"
   

Start the Server

💡 Usage Tip If you encounter difficulties configuring your client (e.g., Cursor, Windsurf, Cline, etc.), please open an issue on Github here, and I'll personally assist you.

Add this server to your client configuration. For example, in the Claude desktop application, navigate to the folder and manually modify the settings file named claude_desktop_config.json.

On MacOS:

~/Library/Application\ 支持/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Modify the configuration file to look like this:

Basic Usage

{
  "mcpServers": {
    "mcp-server-toolhouse": {
      "command": "uvx",
      "args": ["mcp_server_toolhouse"],
      "env": {
        "TOOLHOUSE_API_KEY": "your_toolhouse_api_key",
        "TOOLHOUSE_BUNDLE": "a_bundle_name"
      }
    }
  }
}

Advanced Usage

{
  "mcpServers": {
    "mcp-server-toolhouse": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/this/folder/mcp-server-toolhouse",
        "run",
        "mcp_server_toolhouse"
      ],
      "env": {
        "TOOLHOUSE_API_KEY": "your_toolhouse_api_key",
        "TOOLHOUSE_BUNDLE": "a_bundle_name"
      }
    }
  }
}

Run the Project Locally

The project is not yet configured for disposable environments like uvx. Run the project locally by cloning the repository:

git clone https://github.com/toolhouse-community/mcp-server-toolhouse.git

Add this tool as an MCP server.

🔧 Debugging Tools

Launch the inspector using MCP Inspector via npm:

npx @modelcontextprotocol/inspector uv --directory /path/to/toolhouse_mcp run toolhouse-mcp

The inspector will display a URL in your browser to access the debugging tools.