Provides a persistent Jupyter kernel for executing code, inspecting variables and dataframes, and checking SQL query plans, enabling agents to work with stateful Python sessions.
Enables interactive Python execution with a persistent IPython kernel through MCP, retaining namespace state and providing structured output logs for agent and tool integrations.
Enables AI agents to execute Python, TypeScript, and JavaScript code in persistent Jupyter kernels with stateful variables and imports across interactions.
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.