Modal MCP Toolbox

MCPOpen SourceMIT39.2

by philipp-eisen • Frontend & UI

A collection of MCP (Model Context Protocol) tools running on Modal that extend LLM capabilities with a Python sandbox and FLUX image generation.

Example Use Cases

1
Execute arbitrary Python code in an isolated, sandboxed environment and return results to the user.
2
Generate images using the FLUX model and supply those images back to the user or task flow.
3
Integrate tool capabilities into MCP-supporting clients (e.g., Claude Desktop or Goose) via a Modal-hosted server.

Description

Modal MCP Toolbox provides small MCP tools that run on Modal to extend LLM toolchains such as Claude Desktop App or Goose. It includes a sandboxed Python code executor and a FLUX-based image generator, and is designed to be wired into MCP-capable clients. The project requires a Modal account and UV/uvx tooling and is intended to let agents call external functionality securely from the client.

Capabilities(2 total)

Tools (2)

run_python_code_in_sandbox

Runs python code in a safe environment and returns the output. Usage: run_python_code_in_sandbox("print('Hello, world!')") run_python_code_in_sandbox("import requests print(requests.get('https://icanhazip.com').text)", requirements=["requests"])

code:string*requirements:anypython_version:stringmount_directory:anypull_files:any

generate_flux_image

Let's you generate an image using the Flux model.

prompt:string*

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D49/100

5/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelUnknown

Capabilities2 Tools / 0 Prompts / 0 Resources

Ownerphilipp-eisen

CategoryFrontend & UI

DependenciesStandalone

Set Your Username