PRIMS (Python Runtime)

PRIMS (Python Runtime Interpreter MCP Server) provides AI assistants with secure Python code execution capabilities through an isolated sandbox environment built with FastMCP and Docker. The implementation creates session-persistent workspaces where code runs in virtual environments with configurable pip requirements, supports mounting remote files for data analysis workflows, and automatically captures output artifacts like plots and CSV files that can be served via HTTP endpoints or uploaded to presigned URLs. Built by Hileamlak Mulugeta Yitayew with comprehensive tooling including workspace inspection, file mounting, and artifact persistence, PRIMS serves developers needing reliable Python execution for data science workflows, AI assistants requiring computational capabilities with file I/O, and applications where secure code sandboxing with session persistence is essential for multi-step analytical tasks.