Toolhouse MCP Server

The official Python SDK for the Toolhouse API

Local serverstdioPython

What is the Toolhouse MCP server?

The official Python SDK for the Toolhouse API. The toolhouse mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 1 defined tool rather than through you.

What it actually does

Welcome to the Toolhouse Python SDK documentation. This guide will help you get started with integrating and using the SDK in your project.

The Toolhouse API provides access to various AI-powered tools and services, that you can find on Toolhouse.

Adding it to your client

toolhouse on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • Providers — Toolhouse works with the widest possible range of LLMs across different providers. By default, the Toolhouse API will work with any LLM that is

Configuration

You will need 4 environment variables: TOOLHOUSE_API_KEY, YOUR_API_KEY, OPENAI_API_KEY, TH_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the toolhouse mcp server does with a few real requests.

When to reach for it

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Toolhouse's toolset — Providers — is a fair guide to whether it matches your workflow.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
ProvidersToolhouse works with the widest possible range of LLMs across different providers. By default, the Toolhouse API will work with any LLM that is compatible with the OpenAI chat completions API.

How to install the Toolhouse MCP server

{
  "mcpServers": {
    "toolhouse-2": {
      "command": "uvx",
      "args": ["toolhouse"],
      "env": {
        "TOOLHOUSE_API_KEY": "your-value",
        "YOUR_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "TH_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
TOOLHOUSE_API_KEYCredential the server authenticates with.Yes
YOUR_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
TH_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Toolhouse to Providers.

Frequently asked questions

It connects Toolhouse to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Providers) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Toolhouse directly.