Jupyter MCP Server is a mature, well-documented open-source MCP server maintained by Datalayer, focused on letting AI agents operate Jupyter Notebooks in real time. Its strengths are multimodal output, multi-notebook support, execution that adapts from cell output feedback, and the ability to route execution to a dozen-plus cloud sandbox backends. The main caveats are that agents can execute arbitrary code, so tokens and network exposure must be managed carefully, and that code-sandboxes plus the mcp SDK have strict version pairing requirements that should be checked before upgrading.
Strongest · Setup experience 15/20 Weakest · Reliability 10/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Python · Docker · Hosted (no local runtime)
JUPYTER_URL
URL of your Jupyter service (e.g. http://localhost:8888), pointing at your running JupyterLab/Jupyter Server.
JUPYTER_TOKEN
Jupyter auth token, set via --IdentityProvider.token when starting the server.
DOCUMENT_TOKEN
Separate auth token for the document service.
CODE_SANDBOX_TOKEN
Auth token for the code sandbox service.
DAYTONA_API_KEY
API key required for the Daytona sandbox engine, obtained from Daytona.
E2B_API_KEY
API key required for the E2B sandbox engine, obtained from E2B.
CWSANDBOX_API_KEY
API key required for the CoreWeave sandbox engine.
CLOUDFLARE_SANDBOX_API_KEY
API key required for the Cloudflare sandbox engine.
ALLOW_IMG_OUTPUT
Set to true to allow image outputs; set false if your LLM lacks multimodal support.
DOCUMENT_URL
Separate URL for the notebook document service (used when storage and execution are split).
DOCUMENT_ID
Path to the default notebook, relative to the JupyterLab start directory; omit to select interactively.
CODE_SANDBOX_URL
URL of the code sandbox service (e.g. JupyterHub).
SANDBOX_VARIANT
Selects the sandbox engine, e.g. jupyter-server, datalayer, e2b, kaggle.
SANDBOX_ENVIRONMENT
Optional cloud environment name override (e.g. ai-agents-env) for Datalayer-style engines.
CLOUDFLARE_SANDBOX_API_URL
URL of the Cloudflare sandbox API.
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": ["jupyter-mcp-server@latest"],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "MY_TOKEN",
"ALLOW_IMG_OUTPUT": "true"
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "MY_TOKEN",
"ALLOW_IMG_OUTPUT": "true"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add jupyter -e JUPYTER_URL=http://localhost:8888 -e JUPYTER_TOKEN=MY_TOKEN -e ALLOW_IMG_OUTPUT=true -- uvx jupyter-mcp-server@latest
Run it in a terminal; replace any <…> placeholders with your own values first.
After connecting your MCP client, the tool list should include launch_sandbox, list_sandboxes, use_sandbox and terminate_sandbox; calling list_sandboxes confirms the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Jupyter MCP Server is an MCP server developed by Datalayer (BSD 3-Clause licensed) that lets AI clients connect to and manage Jupyter Notebooks in real time. It offers live view of notebook changes, smart execution that adjusts from cell output feedback, full notebook context awareness, multimodal output support (images, plots, text), and multi-notebook switching. It works with any MCP client (Claude Desktop, Cursor, Windsurf, and more) and with any Jupyter deployment such as a local JupyterLab or JupyterHub. Through the optional jupyter_mcp_sandboxes extension, code execution can be routed to sandbox engines including Datalayer, Kaggle, Google Colab, Modal, Daytona, E2B, CoreWeave and Cloudflare. The project also ships JupyterLab integration (enabled by default), a jupyter-cite prompt, OAuth 2.1 sign-in, and OpenTelemetry-based observability.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision ef47e8b9c9bf Data synced 2026-10-19 Read the FMRS scoring method