Toolhouse

Connect MCP clients to Toolhouse tools via a local server that exposes web scraping, memory, and email tools for MCP workflows.

typescript

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-toolhouse-community_mcp-server-toolhouse": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/this/folder/mcp-server-toolhouse",
        "run",
        "mcp-server-toolhouse"
      ],
      "env": {
        "GROQ_API_KEY": "your_groq_api_key",
        "TOOLHOUSE_API_KEY": "your_toolhouse_api_key",
        "TOOLHOUSE_BUNDLE_NAME": "a_bundle_name"
      }
    }
  }
}

You can connect MCP clients to Toolhouse’s tools using this MCP server. By running the server locally and linking it in your MCP client’s configuration, you get access to a curated set of tools for tasks like web scraping, memory context, and sending emails, all through a standardized MCP workflow.

How to use

You use this server by running it locally and pointing your MCP client at it. The client will load the Toolhouse tools you’ve bundled and expose them as MCP endpoints, enabling your AI workflows to fetch data, store context, or perform actions like sending emails.

How to install

Prerequisites: Node.js and a functioning MCP client setup that supports stdio MCP servers.

Notes on configuration and debugging

Configuration snippets show how to connect the MCP server to your client, and how to supply API keys and bundle names. Debugging is aided by the MCP Inspector, which helps you inspect the runtime interactions between your client and the server.

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

The Inspector will provide a URL to access debugging tools in your browser.

Available tools

web_scrape

Scrape web content and extract data to be used in MCP workflows.

memory

Store and recall context within an MCP session to maintain continuity.

send_email

Send emails as part of MCP-enabled automation and workflows.

Built by

VeilStrat

AI signals for GTM teams