Installation

Installation

JupyDeep is available on PyPI and can be installed via pip (including within uv or conda environments).

uv installation

Using uv as an example, we can set up a project in a new directory named tutorial.

Ensure you have uv is installed. If not, please refer to the uv installation guide.

$ cd tutorial
$ uv init
$ uv add jupyterlab jupydeep "jupyter-mcp-server @ git+https://github.com/yezhenqing/jupyter-mcp-server.git"

Then simply launch JupyterLab as below:

$ uv run jupyter lab --ip=0.0.0.0

The JupyterLab main panel should now display the JupyDeep icon in the right sidebar.

conda installation

For conda, you can create a new environment and then install JupyDeep using pip inside it.

$ conda create -n jupydeep jupyterlab
$ conda activate jupydeep
$ (jupydeep) pip install "jupyter-mcp-server @ git+https://github.com/yezhenqing/jupyter-mcp-server.git" jupydeep

Note

The original jupyter-mcp-server rely on jupyter-server-nbmodel, which suffers from several known issues. In particular, Issue #65 prevents notebooks from executing smoothly.

In both uv and conda, you can install any additional packages you need (such as seaborn for data analysis).