Modal MCP Toolbox MCP Server

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

Local serverstdioPython

What is the Modal MCP Toolbox MCP server?

This runs against your modal account, so you will need to have a modal account and be logged in. That is what the modal mcp toolbox mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 4 tools. What each one is for:

  • 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
  • Claude — Got to Settings > Developer in the Claude Desktop App. And click on Edit Config
  • Goose — Then add an extension like in the screenshot below. The important part is to set command to:

What it needs from you

  • A modal account and a configured modal CLI. - UV - 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.

Things to watch

  • 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.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Modal MCP Toolbox's toolset — run_python_code_in_sandbox, generate_flux_image, Claude and 1 more — is a fair guide to whether it matches your workflow. It is maintained by philipp-eisen; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.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
run_python_code_in_sandboxLet's you run python code in a sandboxed environment.
generate_flux_imageGenerate an image using the FLUX model.
ClaudeGot to Settings > Developer in the Claude Desktop App. And click on Edit Config.
GooseThen add an extension like in the screenshot below. The important part is to set command to:

How to install the Modal MCP Toolbox MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • A modal account and a configured modal CLI. - UV - 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.

Example prompts to try

  • Use Modal MCP Toolbox to run python code in sandbox.
  • Use Modal MCP Toolbox to generate flux image.
  • Use Modal MCP Toolbox to Claude.

Frequently asked questions

It connects Modal MCP Toolbox to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (run_python_code_in_sandbox, generate_flux_image, Claude, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Modal MCP Toolbox directly.