MCP.so
Sign In

Python Sandbox MCP Server

@cloudywu0410

Repository

About Python Sandbox MCP Server

A MCP server that enables LLMs to run python code safely in isolated Docker containers.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "python-sandbox-sse": {
      "command": "mcp-proxy",
      "args": [
        "http://localhost:8060/eval"
      ],
      "ssePath": "/eval"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Python Sandbox MCP Server?

A secure Python code execution server that enables LLMs to run Python code safely in isolated Docker containers. It supports stdout capture, Matplotlib plotting with PNG image generation, and real-time communication via Server-Sent Events (SSE). The server uses the Snekbox Docker container for sandboxing, providing a safe environment for code execution. It is designed for integration with MCP-compatible clients such as Claude Desktop.

How to use Python Sandbox MCP Server?

First, clone the repository and install dependencies using uv add -r requirements.txt. Then pull the Snekbox Docker image and start the container with security parameters. Optionally install additional Python packages inside the container. Finally, update your MCP client configuration to point to the local build, e.g., using mcp-proxy with SSE endpoint http://localhost:8060/eval. The server can be configured via environment variables MCP_SERVER_NAME, SNEKBOX_URL, and TEMP_DIR.

Key features of Python Sandbox MCP Server

  • Regular Python code execution with stdout capture
  • Matplotlib plotting with PNG image generation

Comments

Basic information

Category

Reasoning

Transports

stdio

Author

cloudywu0410

Submitted by

cloudywu0410

More Reasoning MCP servers

MCP Sandbox

danstarns

Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.

5

Agenticstore — The Open Source Standard For Local Mcp Tooling

agenticstore

AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 27+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.

4

iFlytek Workflow MCP Server

iflytek

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

28

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

27

mcp-agentic-rag

rukshannet

MCP Server for Agentic RAG applications

4