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.

Demo

Flux Image Generation

🎬Flux Image Generation

Python Code Execution

🎬Python Code Execution

Prerequisites

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.

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

Metadata

Release files for modal-mcp-toolbox 0.1.12

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for modal-mcp-toolbox 0.1.12
File	Size	Uploaded	Provenance
modal_mcp_toolbox-0.1.12.tar.gz	8.2 MB	Feb 24, 2025	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for modal-mcp-toolbox 0.1.12
File	Interpreter	ABI	Platform	Reset
modal_mcp_toolbox-0.1.12-py3-none-any.whl 7.5 kB Feb 24, 2025 Without provenance	Python 3	none	any	Details

Total release size: 8.3 MB

Release files / modal_mcp_toolbox-0.1.12.tar.gz

Download URL	modal_mcp_toolbox-0.1.12.tar.gz
Size	8.2 MB
Tags	Source
SHA-256 checksum How to use checksums	`21489b8acde7e6677168671f571bc9614710f15377700c20853f141136a11393`
BLAKE2b-256 checksum How to use checksums	`366d4f81b94534eb8e29073a8a8f5c0e43f26de4ecc678be77c924e671c1d917`
Upload date	Feb 24, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`uv/0.6.2`

Release files / modal_mcp_toolbox-0.1.12-py3-none-any.whl

Download URL	modal_mcp_toolbox-0.1.12-py3-none-any.whl
Size	7.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0dab011f828323fad5d45630311f0d5415d2ff488147dfe648df54495e43c585`
BLAKE2b-256 checksum How to use checksums	`e169c0a09b3045640af9d8f91bf8eb04a7976575c0aed80dd6348eaa7a4e9455`
Upload date	Feb 24, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`uv/0.6.2`

Security for modal-mcp-toolbox 0.1.12

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.