Python Exec Sandbox MCP Server
io.github.lu-zhengda/mcp-python-exec-sandbox
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Python Exec Sandbox MCP server?
Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.
How to install Python Exec Sandbox
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"mcp-python-exec-sandbox": {
"command": "uvx",
"args": [
"mcp-python-exec-sandbox"
]
}
}
}Related MCP servers

Virtual Filesystem
PostgreSQL-backed virtual filesystem for agents: session isolation, shared stores, POSIX ops, RLS.

Interactive EDA sessions for semiconductor design via AI—connect Claude to OpenROAD layout tools.

Sketchdex
An MCP server that lets AI agents draw hand-drawn Excalidraw diagrams as files on your machine.
Query, navigate, and verify scenes on the Colpero spatial network from any MCP client.
View repository →Verify a Chinese supplier before you pay: company identity, status, risk signals. x402 per call.
Private-market data across Southeast Asia via the Alternatives Partner API v3

