jupyter_mcp
Kernel-attached MCP server for Jupyter EDA workflows for coding agents
An MCP server designed for AI agents to interact efficiently with Jupyter notebooks using a dependency DAG and named cells. It provides features like minimal re-execution, condensed outputs to save context, and automated cell summaries to help agents navigate complex notebooks.
- Built with
- Fable 5NEWHaiku 4.5Strong
The source context explicitly credits Fable 5 as the build model, and the README confirms Claude-based features for the tool's operation.
post says 'fable is truly something else'; source explicitly credits claude-haiku-4-5 (README mentions 'Lazy, batched claude-haiku-4-5 summaries')
- Posted by
- We haven't verified this person made this build — attribution is our best guess from public sources.
- Discovered
- Discovered onX
- Source date
- Published on X Jul 6, 2026
- Listed
- Added to Dropday 3h ago
- Evidence
- Strong
Public GitHub repository with a complete directory structure, pyproject metadata, and detailed implementation documentation for the MCP server.