ipynb-mcp
Related Servers
Alternatives to ipynb-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables AI agents to safely read, edit, and execute local Jupyter notebooks without running a separate service. Edits are guarded by compare-and-swap hashes and execution resumes or replays kernel state, so long-running cells aren't needlessly re-run.638 npm3MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to browse, create, edit, and execute Jupyter notebook cells against local .ipynb files or a running Jupyter Server, including kernel interrupt/restart and notebook export. Outputs (text, tables, PNG images) are written back to the notebook and returned to the conversation.511 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to execute Jupyter notebook cells with persistent kernel state, output persistence, and structured JSON control surface.2-
- AlicenseAqualityDmaintenanceEnables AI agents to create, read, edit, and execute Jupyter notebook cells, manage kernels, and connect to remote Jupyter servers.2124 PyPIMIT
- AlicenseAqualityDmaintenanceEnables AI assistants to read, edit, and execute Jupyter notebook files (.ipynb) with live kernel output, without requiring JupyterLab.17MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to read, edit, execute cells, and capture outputs from Jupyter notebooks directly within VS Code or Cursor via the Model Context Protocol.5 npm18MIT
TDQS
Scored across 6 tools
Each tool targets a distinct operation: reading metadata, reading a cell, adding, editing, running, or restarting the kernel. There is minimal overlap and an agent can clearly select the right tool for the intended action.
Most tools follow a clear verb_noun pattern: read_cell, add_cell, edit_cell, run_cell, restart_kernel. notebook_info is the only slight deviation, being noun_noun rather than get_notebook_info, but it remains readable and consistent with the overall style.
Six tools is a well-scoped set for notebook manipulation. Each tool serves a clear and necessary purpose without unnecessary bloat.
The core lifecycle of reading, adding, editing, and executing cells is covered, and restart_kernel handles execution-state resets. However, a delete_cell operation is missing, which is a notable gap for editing workflows, and there is no way to reorder cells.