Exposes the Jupyter notebooks open in VS Code to MCP-compatible AI agents, letting them edit cells in the open editor and execute them in the live kernel without file conflicts. Agents can make partial edits, track stale cells, inspect variables, and manage kernels while preserving the user's interpreter choices and unsaved work.
Exposes Jupyter notebook operations as MCP tools over plain HTTP, allowing AI agents to explore, edit, run, and debug notebooks in a live VS Code session using local or remote kernels.
Enables external AI coding agents to use a running VS Code instance for IDE-aware file operations, project-wide symbol renames, file moves that update imports, code analysis, diagnostics, and formatting through a local MCP endpoint. Provides configurable tool categories, optional bearer-token authentication, and protections against DNS rebinding and cross-origin browser requests.