Python Sandbox
Provides a browser-compatible Python execution environment with package management capabilities for running code snippets safely w
MCP-Run-Python provides a sandboxed environment for executing Python code through a standardized interface. Built with TypeScript and Pyodide, it allows AI assistants to run Python snippets safely in a browser-compatible environment, supporting package installation through PEP 723 script metadata. The server offers both SSE and stdio transport options, handles dependency management automatically, and returns execution results in a structured XML format containing stdout, stderr, and return values. This implementation is particularly valuable for interactive code examples, educational tools, and AI assistants that need to demonstrate or test Python code without requiring a full backend Python environment.
Source
Repository: https://github.com/pydantic/pydantic-ai/tree/HEAD/mcp-run-python
Maintain Python Sandbox?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/pydantic-pydantic-ai?ref=badge) Related mcp
Chrome Browser Automation Provides browser automation and semantic search capabilities through Chrome extension integration, enabling intelligent web elemen
Playwright Automate web browsers for testing, scraping, and visual analysis.
Browserbase Automate web browsers remotely on a cloud environment.
DBHub (Universal Database Gateway) Provides a universal database gateway for connecting to PostgreSQL, MySQL, SQLite, and DuckDB, enabling table browsing, schema ins
Search (UI-TARS) Web search with multiple search engines and browser automation
Playwright Browser Automation Enables web browser control for navigating websites, capturing page snapshots, interacting with elements, and taking screenshots t