Jupyter MCP Server
Servidor MCP de Datalayer
Read, edit and execute cells in live Jupyter notebooks from your AI assistant.
Instalar Jupyter MCP Server
Se ejecuta en tu equipo. Tu cliente lo inicia con este comando:
Requiere uv (Python) en tu equipo. Los pasos de configuración de abajo muestran dónde va el comando en cada cliente.
Compartir este servidor
Abre esta página, con el comando de instalación y los pasos de configuración.
mcp.tc/i/jupyterDescripción
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.
Qué puedes hacer
- 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
Herramientas
Los servidores locales muestran sus herramientas cuando están en marcha, y este no publica su lista por adelantado. Tu cliente las muestra después de añadirlo.
Prompts de ejemplo
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
Configuración
Todos los clientes inician Jupyter MCP Server en tu equipo con el mismo comando. Elige el tuyo; la página recuerda tu elección.
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
Añadir a Cursor (se abre en una pestaña nueva)
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 (se abre en una pestaña nueva)
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.
Preguntas frecuentes
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 y 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.
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.
Insertar
Muestra Jupyter MCP Server en un README o en tu web. Cada inserción enlaza a esta página, usa el comando de instalación del servidor y no instala cookies. Cómo funcionan las inserciones
Insignia para README
[](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>Sigue el modo claro u oscuro de quien lee. Añade ?theme=light o ?theme=dark para fijarlo, o ?style=compact para mostrar el símbolo sin la palabra.
Tarjeta para web
<script src="https://mcp.tc/w/jupyter.js" async></script>La tarjeta aparece donde esté la etiqueta. Añade data-theme="dark" o data-size="compact" a la etiqueta para cambiarla. El archivo contiene todo lo que necesita, así que no hace otras solicitudes ni instala 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>Úsalo en páginas que no permiten scripts. Añade ?theme=light o ?theme=dark a la dirección para fijar los colores.
JSON
La ficha como datos para tus propias páginas y herramientas: nombre, descripción corta, comando de instalación, herramientas y los enlaces «Add to». Cualquier web puede leerla (CORS abierto).
https://mcp.tc/i/jupyter.jsonmcp.tc no tiene relación con Datalayer. Esta página se creó a partir de los metadatos públicos de Jupyter MCP Server, comprobados por última vez el 3 oct 2026, y un modelo de IA escribió la descripción, así que puede contener errores. Los nombres y marcas pertenecen a sus titulares. ¿Algo no cuadra? Reportar esta ficha.