Hosted MCP server/Development

Jupyter MCP server

Hosted at mcp.datalayer.run·Streamable HTTP

Jupyter MCP connects an agent to Jupyter notebooks. The Datalayer-hosted endpoint at https://mcp.datalayer.run/mcp executes notebooks and code on Datalayer's servers, not on the user's machine, and requires OAuth sign-in with scope approval; headless CLI and script clients can use a personal access token. The provider also ships a local pip-installed server that runs over stdio for a JupyterLab instance on the user's own machine. The repository is the source for both paths.

mcp.datalayer.run Streamable HTTP OAuth sign-in (hosted) or personal access token Server not checked yet Reviewed 2026-11-16
About

Where it fits

Data scientists who want an agent to inspect, edit and run notebooks, with a clear choice between Datalayer-hosted execution and a local JupyterLab.

  • Inspect and edit notebook cells through an agent.
  • Run notebook code on Datalayer's hosted service.
  • Use the local stdio server against a machine-local JupyterLab.

A remote MCP server advertises tools to your client. The provider controls the tools, the data they can reach, and the permissions they need. Read the provider's docs before you use it with private data.

Setup

Install it in your client

Choose a client, run the command or use the one-click install, then verify the connection. The endpoint uses Streamable HTTP.

All client guides
  1. 01

    Run this command in your terminal

    This adds Jupyter as a remote Streamable HTTP server in Claude Code.

    Claude Code
    claude mcp add --transport http jupyter https://mcp.datalayer.run/mcp --scope project
  2. 02

    Verify the connection

    Run claude mcp list, or open /mcp in a Claude Code session.

    Learn more about MCP in Claude Code

More clients, including project and global config files, are in the sidebar.

Connection

Endpoint and configuration

Endpoint
https://mcp.datalayer.run/mcp
Host
mcp.datalayer.run · /mcp
Transport
Streamable HTTP
Authentication
OAuth sign-in (hosted) or personal access token
Server name
jupyter
Listing type
Community or directory listing

The installer uses the server name jupyter. If you add the endpoint by hand, keep the same name so the guide and your config match.

Verification

Check the connection

After you add the server, confirm that the client can see its tools and that one small request returns what the provider describes.

  1. 1
    Open the tool list.

    Restart the client or start a new session. Confirm that jupyter appears and that the tools match the provider documentation.

  2. 2
    Run one small request.

    Start with: Inspect and edit notebook cells through an agent. Check the result before you give the server more access.

  3. 3
    Check permissions.

    Review the OAuth scopes or API-key permissions, then remove the server and revoke its token when you no longer need it.

Server not checked yet

We checked the provider's page, not the MCP connection itself. No MCP sign-in or tool call was attempted. A provider page is linked but was not included in the automated check. Open it before setup.

Troubleshooting

Common failure modes

These are the problems to check first. If the provider changes its endpoint or authentication flow, use its documentation as the source of truth.

  • The sign-in window closes without returning. Allow pop-ups and finish the provider login in the same browser.
  • The server connects but its tools are missing. Remove it, add it again, and approve the scopes the provider lists.
  • Your client does not support Streamable HTTP. Use a client that does, and confirm the provider's current endpoint and transport in its docs.
Safety

Before you connect

Remote means provider access
  • The provider can see the requests and data your agent sends through the server.
  • Review OAuth scopes and API-key permissions. Start read-only if the provider offers it.
  • Use project scope for repository-specific servers; use global scope for personal tools.
  • Remove the server and revoke its token when you stop using it.
Review path

Check the connection before a real task

These guides cover the decisions that a provider description cannot answer: endpoint ownership, scopes, tool access, and a read-only test.

Reference

Provider source

Setup requirements, available tools, and rate limits live with the provider. Use the source link as the authority for this server.

Jupyter repositoryhttps://github.com/datalayer/jupyter-mcp-server