# datalayer/jupyter-mcp-server

🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.

Repository: https://github.com/datalayer/jupyter-mcp-server
Canonical: https://ross.abutalabs.com/products/jupyter-mcp-server
Homepage: https://jupyter-mcp-server.datalayer.tech
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: jupyter, mcp-server, ai, mcp, tools
Last push: 2026-09-02T08:35:18+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 100, longevity 40
- inputs: {"age_days": 567, "days_push": 0, "days_rel": 1, "gap_med": 1.0, "n_releases_24m": 51}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1270, forks 194 (observed 2026-09-03T02:15:11.161795+00:00)

## What it is
A Model Context Protocol (MCP) server that lets AI agents connect to, edit, and execute Jupyter Notebooks in real time. It supports STDIO and Streamable HTTP transports, works with any Jupyter deployment or hosted code sandbox, and is also available as a hosted endpoint from Datalayer.

## Use cases
- let an AI agent run and edit Jupyter notebooks
- connect Claude Code to Jupyter for data analysis
- execute notebook cells and get output feedback from an LLM
- use Jupyter as a code sandbox for AI agents
- automate data analysis and visualization in notebooks
- manage multiple notebooks from an AI assistant

## When to choose
- you want an AI agent to work directly in Jupyter notebooks with real-time feedback
- you need multimodal cell outputs (plots, images, text) returned to an LLM
- you want a self-hosted or hosted MCP server compatible with STDIO and HTTP transports
- you need scalable code sandboxes from local to cloud providers

## When to avoid
- you don't use Jupyter or notebook-based workflows
- you need a general-purpose code execution sandbox without notebooks
- your MCP client supports neither STDIO nor Streamable HTTP

## Facets
- artifact type: service
- maturity: active
- function: mcp, llm-inference, agent-framework, sdk
- domain: large-language-models, data-science, developer-tools
- platform: python, self-hosted, cross-platform
- tags: jupyter, mcp-server, notebook-automation, code-execution, claude-code, data-analysis, code-sandbox, ai-agents, docker, web-server

## Member repositories
- datalayer/jupyter-mcp-server (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:11.161795+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:18.607565+00:00, confidence not recorded.
  - readme: https://github.com/datalayer/jupyter-mcp-server (fetched 2026-09-03T02:15:11.161795+00:00, sha 4f08992cf717)
  - homepage: https://jupyter-mcp-server.datalayer.tech (fetched 2026-08-29T12:16:51.001399+00:00, sha e143294668ff)
  - registry_pypi: https://pypi.org/pypi/jupyter-mcp-server/json (fetched 2026-08-29T12:16:51.013539+00:00, sha 0adaf2b439ab)
  - site_page: https://jupyter-mcp-server.datalayer.tech/releases (fetched 2026-08-29T12:16:51.010512+00:00, sha 0bb8ab0cebd8)
- Data as of 2026-08-30T08:39:29.467469+00:00.