0
0
via GitHub · Posted Jul 15, 2026 · 1 min read
MCP Server

A collection of tools for your LLMs that run on Modal

26Stars
5Forks
2Open issues
2Watching
Python MIT 0.1.12 Updated 1 year ago
View on GitHub

A Model Context Protocol server providing sandboxed Python code execution and FLUX image generation tools that run on Modal infrastructure. Integrates with Claude Desktop, Goose, and other MCP-compatible clients to extend LLM capabilities.

0 comments

README

Modal MCP Toolbox 🛠️

smithery badge

A collection of Model Context Protocol (MCP) tools that run on Modal. This let's you extend the capabilities of your LLM in tools such as Goose or the Claude Desktop App.

Tools

  • run_python_code_in_sandbox: Let's you run python code in a sandboxed environment.
  • generate_flux_image: Generate an image using the FLUX model.

Demo

Flux Image Generation

🎬Flux Image Generation

Python Code Execution

🎬Python Code Execution

Prerequisites

This runs against your modal account, so you will need to have a modal account and be logged in.

Installation

Installation depends on the client that uses the MCP. Here is instructions for Claude and Goose.

Claude

Got to Settings > Developer in the Claude Desktop App. And click on Edit Config. 🖼️Claude Settings

Add the config for the mcp server. My config looks like this:

{
  "mcpServers": {
    "modal-toolbox": {
      "command": "uvx",
      "args": ["modal-mcp-toolbox"]
    }
  }
}

Goose

Go to Settings and Click on Add.

🖼️Goose Settings

Then add an extension like in the screenshot below. The important part is to set command to:

uvx modal-mcp-toolbox

The rest you can fill in as you like.

🖼️Goose MCP Settings

Installing via Smithery (not working currently)

To install Modal MCP Toolbox for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @philipp-eisen/modal-mcp-toolbox --client claude

Comments (0)

Sign in to join the discussion.

No comments yet

Be the first to share your take.