Jupyter MCP Server
MCP server by Datalayer
Read, edit and execute cells in live Jupyter notebooks from your AI assistant.
Install Jupyter MCP Server
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/jupyterAbout
Connects an AI assistant to Jupyter notebooks in real time. The assistant can work with notebook cells, edit and document them, and run code for data analysis and visualization. It can target a local JupyterLab or JupyterHub, or cloud code sandboxes.
It runs locally with uvx jupyter-mcp-server@latest, pointed at a running Jupyter server through JUPYTER_URL and JUPYTER_TOKEN. Datalayer also hosts an endpoint at https://mcp.datalayer.run/mcp that uses OAuth sign-in with scoped permissions. The project is BSD-3-Clause licensed.
What you can do
- Read and edit cells in live Jupyter notebooks
- Execute code cells and get the results
- Document and analyze data inside notebooks
- Connect to a local JupyterLab or JupyterHub
- Use the hosted Datalayer endpoint with OAuth sign-in
- Scale code sandboxes from local to cloud providers
Tools
Local servers list their tools once they’re running, so we can’t show them here. Look for the list in its documentation; your client shows them after you add it.
Example prompts
Open my analysis notebook and summarize what each cell does
Add a cell that plots monthly sales from the dataframe and run it
Fix the failing cell in my notebook and re-execute it
Write markdown documentation for the cells in this notebook
Set up
Every client starts Jupyter MCP Server on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio jupyter -- uvx jupyter-mcp-server@latest- Start Claude Code and type
/mcp. jupyter should show as connected.
Add --scope user to make it available in every project.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
]
}
}
}- Save the file and restart Claude Desktop.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
]
}
}
}Needs uv (Python) on your computer.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"jupyter","type":"stdio","command":"uvx","args":["jupyter-mcp-server@latest"]}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"jupyter": {
"type": "stdio",
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
]
}
}
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
]
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add jupyter -- uvx jupyter-mcp-server@latestOr edit ~/.codex/config.toml directly:
[mcp_servers.jupyter]
command = "uvx"
args = ["jupyter-mcp-server@latest"]Needs uv (Python) on your computer.
Gemini CLI
gemini mcp add jupyter uvx jupyter-mcp-server@latestThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": [
"jupyter-mcp-server@latest"
]
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer.
Embed
Show Jupyter MCP Server in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/jupyter)<a href="https://mcp.tc/i/jupyter"><img src="https://mcp.tc/i/jupyter/badge.svg" alt="Jupyter MCP Server on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/jupyter.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/jupyter" title="Jupyter MCP Server on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/jupyter.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Jupyter MCP Server card to your site.
Add the mcp.tc card for Jupyter MCP Server, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/jupyter.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="jupyter"><a href="https://mcp.tc/i/jupyter">Jupyter MCP Server on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/jupyter)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
FAQ
Can I paste mcp.tc/i/jupyter into my MCP client?
No. Jupyter MCP Server runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx jupyter-mcp-server@latest.
Does Jupyter MCP Server need an API key?
No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.
Is Jupyter MCP Server a remote or a local server?
Local. Your client starts it as a process on your computer with uvx jupyter-mcp-server@latest, which needs uv (Python).
What can Jupyter MCP Server do?
You can read and edit cells in live Jupyter notebooks, execute code cells and get the results and document and analyze data inside notebooks.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to Jupyter MCP Server?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Jupyter MCP Server’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Datalayer. This page was built from Jupyter MCP Server’s public metadata, last checked on 3 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.