Safe Local Python Executor

Created By
maxim-saplina year ago
Overview

what is Safe Local Python Executor?

Safe Local Python Executor is a custom Python runtime that provides basic isolation and security for running Python code generated by large language models (LLMs). It wraps Hugging Face's LocalPythonExecutor and exposes it via the Model Context Protocol (MCP) for use in LLM applications.

how to use Safe Local Python Executor?

To use the Safe Local Python Executor, install the required dependencies, clone the repository, and start the server using the command uv run mcp_server.py. Configure your LLM application (like Claude Desktop) to connect to the Python executor.

key features of Safe Local Python Executor?

  • Exposes a run_python tool for executing Python code.
  • Provides safer execution of Python code compared to direct execution.
  • Runs in a virtual environment with a restricted list of imports for enhanced security.

use cases of Safe Local Python Executor?

  1. Running Python code generated by LLMs in a secure environment.
  2. Integrating Python execution capabilities into LLM applications like Claude Desktop.
  3. Providing an alternative to traditional Python interpreters in LLM tools.

FAQ from Safe Local Python Executor?

  • Is the Safe Local Python Executor secure?

Yes! It provides a safer execution environment by restricting imports and running in a controlled virtual environment.

  • How do I install the Safe Local Python Executor?

Follow the installation instructions in the documentation, which include installing uv, cloning the repository, and starting the server.

  • Can I use it with any LLM application?

Yes! It is designed to work with any MCP compatible client, including Claude Desktop.

Server Config

{
  "mcpServers": {
    "safe-local-python-executor": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp_local_python_executor/",
        "run",
        "mcp_server.py"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
maxim-saplin
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago