A production-grade MCP server providing a persistent Python REPL with multi-session support, sandboxing, and timeout protection, enabling LLM agents to execute Python code across multiple turns with variables that persist between calls.
MCP server for secure, session-based Python code execution in Docker containers, enabling LLM applications to run code, manage state, and access files.
Provides a persistent, stateful IPython execution environment for MCP clients, allowing agents to run Python code, define functions and classes, and maintain state across calls. It includes tools for execution, inspection, dynamic tool registration, and robust timeout/recovery handling.
Provides persistent IPython shell sessions per conversation with DataFrame-centric architecture, enabling stateful data analysis, CLI tool execution, and integration of external MCP servers within the same workspace context.
