Safe Local Python Executor
@maxim-saplin
About Safe Local Python Executor
Stdio MCP Server wrapping custom Python runtime (LocalPythonExecutor) from Hugging Faces' `smolagents` framework. The runtime combines the ease of setup (compared to docker, VM, cloud runtimes) while providing safeguards and limiting operations/imports that are allowed inside the
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"safe-local-python-executor": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp_local_python_executor/",
"run",
"mcp_server.py"
]
}
}
}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 Safe Local Python Executor?
Safe Local Python Executor is an MCP server (stdio transport) that wraps Hugging Face's LocalPythonExecutor to provide a safer Python runtime for executing code generated by LLMs locally, without needing Docker or a VM. It is intended for LLM apps like Claude Desktop, Cursor, or any MCP-compatible client.
How to use Safe Local Python Executor?
Install via Smithery (npx -y @smithery/cli install @maxim-saplin/mcp_safe_local_python_executor --client claude) or manually: install uv, clone the repo, and run uv run mcp_server.py. Then configure Claude Desktop by adding the tool to its configuration file with the command uv and appropriate arguments.
Key features of Safe Local Python Executor
- Exposes
run_pythontool for safe code execution - Runs locally with no Docker or VM required
- Restricts imports to a safe list (collections, math, etc.)
- No file I/O operations allowed
- Uses Hugging Face's LocalPython
Basic information
More Cloud & Infrastructure MCP servers
Cloudflare MCP Server
cloudflare🐋 Docker MCP server
ckreilingMCP server for Docker
Mcp K8s Go
strowkMCP server connecting to Kubernetes
AWS MCP Servers
awslabsOpen source MCP Servers for AWS
Query | MCP server for Supabase
alexander-zuevQuery MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
Comments