Python Exec Sandbox MCP Server

by lu-zhengda Your server? Claim it

local only

Python Exec Sandbox runs on your own machine — the client starts it, so there is no endpoint to ping. 128 installs a week from pypi. Last commit 9 Feb 2026.

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

Installs per day peak 56 · avg 20 · -19% w/w

a month agotoday

128

Installs / week

pypi · mcp-python-exec-sandbox

Stars

2 open issues

9 Feb 2026

Last commit

0 releases in 90 days

MIT

License

Python

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/mcp_python_exec_sandbox/executor.py:25, src/mcp_python_exec_sandbox/sandbox_docker.py:30, src/mcp_python_exec_sandbox/server.py:50 и ещё 5

            result = subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-python-exec-sandbox -- uvx mcp-python-exec-sandbox

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-python-exec-sandbox": {
      "args": [
        "mcp-python-exec-sandbox"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-python-exec-sandbox]
command = "uvx"
args = ["mcp-python-exec-sandbox"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-python-exec-sandbox": {
      "args": [
        "mcp-python-exec-sandbox"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp-python-exec-sandbox": {
      "args": [
        "mcp-python-exec-sandbox"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Python Exec Sandbox

same job, measured the same way

Runeward

by runewardd

Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.

local only

Sandbox Env MCP

by hs3434

Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.

71 installs/wk local only

Arithym

by arithym

Precision math engine for AI agents. 203 exact methods. Zero hallucination.

answering

Jacobian

by morluto

Executable mathematics and independent verification for AI agents.

352 installs/wk local only

agenthold

by edobusy

Shared versioned state for multi-agent AI workflows

271 installs/wk local only

Agent Workspace MCP

by hrrodan

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

local only

RLM Tools

by stefanoshea

Persistent Python sandbox for token-efficient codebase exploration in MCP clients

31 installs/wk local only

Mailbuttons (mbag.ai)

by mailbuttons

Governed email for AI agents (Mailbuttons / mbag.ai): sandbox inboxes, policy gate, audit log.

37 installs/wk answering

Python Exec Sandbox — questions

Answers built from our own checks of this server.

Why is there no uptime for Python Exec Sandbox?

Python Exec Sandbox runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-python-exec-sandbox was installed 128 times last week.

How do I connect Python Exec Sandbox?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcp-python-exec-sandbox straight from pypi; nothing to host, nothing to sign up for.

How many people use Python Exec Sandbox?

The pypi package mcp-python-exec-sandbox was installed 128 times in the last week. Week over week that is -19%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Python Exec Sandbox open source?

Yes — it is published under the MIT licence, written in Python, 1 stars on GitHub and 2 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.