Skip to main content

Serve

Serve with Python​

Clone the repository and use pip install -e . or just install the jupyter-mcp-server package from PyPI with pip install jupyter-mcp-server.

Then, you can start JupyterLab and Jupyter MCP Server with the following commands.

make jupyterlab
make start-streamable-http

Serve with Docker​

You can also run the Jupyter MCP Server using Docker. Use the following command to start the server on MacOS.

docker run \
  --network=host \
  -e DOCUMENT_URL="http://localhost:8888" \
  -p 4040:4040 \
  datalayer/jupyter-mcp-server:latest \
  --transport streamable-http
note

You can set the DOCUMENT_URL (JupyterLab Server URL), RUNTIME_TOKEN, and DOCUMENT_ID environment variables to configure the server with the -e option in the docker run command. If not set, the defaults will be used. Refer to the server configuration for more details on the available environment variables and their defaults.

Use the following command to start the server on Linux.

docker run \
  --network=host \
  -e DOCUMENT_URL="http://localhost:8888" \
  -p 4040:4040 \
  datalayer/jupyter-mcp-server:latest \
  --transport streamable-http