Jupyter MCP Server
Lets an assistant open, read and edit Jupyter notebooks in real time: insert, edit and delete cells, execute code on the kernel, and see outputs including plots and images.
- Maintained by
- Community (Datalayer)
- Hosting
- Runs locally on your machine
- Authentication
- API key or credentials (environment variables)
- Last checked
Needs a running JupyterLab (with jupyter-collaboration installed) or JupyterHub server.
How to connect the Jupyter MCP server
Pick your AI client and paste the snippet. Swap the YOUR_… placeholders for your own values. New to this? Our guide to how MCP clients and servers fit together explains what each piece does.
Claude Code
claude mcp add --env JUPYTER_URL=http://localhost:8888 --env JUPYTER_TOKEN=YOUR_JUPYTER_TOKEN --transport stdio jupyter \
-- uvx jupyter-mcp-server@latestClaude Desktop
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "YOUR_JUPYTER_TOKEN"
}
}
}
}Fully quit and reopen Claude Desktop after saving.
Full Claude Desktop setup guide →Cursor
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "YOUR_JUPYTER_TOKEN"
}
}
}
}VS Code
{
"servers": {
"jupyter": {
"type": "stdio",
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "YOUR_JUPYTER_TOKEN"
}
}
}
}Frequently asked questions
What is the Jupyter MCP server?
It is a Model Context Protocol (MCP) server — a small piece of software that gives AI assistants like Claude a secure, governed connection to Jupyter. Lets an assistant open, read and edit Jupyter notebooks in real time: insert, edit and delete cells, execute code on the kernel, and see outputs including plots and images.
Is there an official Jupyter MCP server?
Not from Jupyter itself. This one is community-maintained (Datalayer). It is widely used, but review the repository and pin a version before relying on it in production.
Is the Jupyter MCP server hosted, or do I run it myself?
It runs locally. Your AI client starts it on your own machine with uvx, and it talks to the client over standard input and output rather than the network.
Do I need an API key for the Jupyter MCP server?
Yes. The local server reads JUPYTER_URL, JUPYTER_TOKEN from its environment, so you create those credentials first and add them to your client's config.
What can an AI assistant actually do with Jupyter?
Through this server an assistant can work with manage notebooks, edit cells, execute code, read outputs, list kernels — reading from and acting on Jupyter directly instead of you copy-pasting between windows. What you allow it to do is controlled by the permissions you grant.
How do I set this up for my business?
The setup section above has copy-paste config for Claude Code, Claude Desktop, Cursor and VS Code. Once it is running against real systems, the question becomes what catches it when it acts wrongly, which is what Crox's Safety Diagnostic looks at.
New to MCP? Start with our plain-English guide to the Model Context Protocol or see how to connect AI to your business tools without writing code .
Already running this in production?
An agent with a live connection to your tools is a model that can act. Crox looks at what catches it when it acts wrongly: the layers around it, who can stop it, and where a near miss gets reported. Two days, one team, one model.