The Modal MCP Toolbox server extends LLM capabilities by providing two main tools:
Run Python Code in a Sandbox: Execute Python code in a safe, isolated environment. Supports installing packages, specifying Python versions, and handling file operations.
Generate Images: Create images based on textual prompts using the Flux model.
Modal MCP Toolbox 🛠️
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.
Related MCP server: Optimized Memory MCP Server V2
Demo
Flux Image Generation
Python Code Execution
Prerequisites
A modal account and a configured modal CLI.
A client that supports MCP. Such as the Claude Desktop App or Goose
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.
Add the config for the mcp server. My config looks like this:
Goose
Go to Settings and Click on Add.
Then add an extension like in the screenshot below. The important part is to set command to:
The rest you can fill in as you like.
Installing via Smithery (not working currently)
To install Modal MCP Toolbox for Claude Desktop automatically via Smithery: