Server facts
jupyter-mcp-server
Project
- Author
- ChengJiale150
- License
- Not specified
- Category
- Data & Analytics
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 9
- Last commit
- Data as of
Tags
- Jupyter
- mcp
- notebook management
Overview
Notebook-based analysis can move between cell inspection, code changes, and execution through Jupyter MCP Server. Data scientists working with AI in MCP-compatible IDEs or CLI clients can connect notebooks and their kernels, then manage several notebook sessions together. Notebook listings identify active connections, while cell listings expose structure and execution status before more targeted inspection. Individual cells can be read, inserted, replaced, deleted, or executed, with results available as text, images, or tables. Whole-notebook source reading is reserved for explicit user requests and excludes outputs.
For iterative work, append_execute_cell combines adding a final cell with running it, while execute_temporary_cell runs exploratory snippets without saving them into the notebook. Temporary execution supports debugging, intermediate-value checks, and statistical calculations, but its documented scope excludes lengthy jobs and imports or assignments that affect later notebook execution. Cell replacements return a change comparison, and restarting a notebook kernel clears imported packages and variables. The service uses stdio transport and requires connection details for a Jupyter server; viewing image results also depends on the client's ability to receive and interpret them.
jupyter-mcp-server setup notes
- jupyter-mcp-server records stdio only; confirm a network transport upstream before planning remote access.
- jupyter-mcp-server has no recorded license; confirm reuse terms in its repository.