ajlab

Agent-ready JupyterLab.

ajlab is a small meta-package that installs JupyterLab plus a few extensions useful for agent workflows, and ships some defaults under etc/jupyter/labconfig.

Minimum versions (see pyproject.toml):

• jupyterlab >=4.6.1
• jupyter-docprovider >=3.0.0 and jupyter-server-ydoc >=3.0.0
• jupyter-server-mcp >=0.3.0
• jupyterlab-commands-toolkit >=0.2.0

• Hidden files shown in the file browser.

pip install ajlab

Once installed, start JupyterLab with:

jupyter lab

Agent connectivity is provided by jupyter-server-mcp, which runs inside JupyterLab and exposes an MCP endpoint (default port 3001) that any MCP client can connect to.

The recommended way to connect a client is the stdio proxy, which auto-discovers the running Jupyter MCP server and bridges stdio to its HTTP endpoint. It keeps working unchanged when several Jupyter servers run side by side or when the port is assigned dynamically. The proxy is installed alongside ajlab, so to wire it up to Claude Code from a JupyterLab terminal:

claude mcp add jupyter -- jupyter-server-mcp-proxy

From an environment where jupyter-server-mcp-proxy is not on the PATH, run it with uvx instead:

claude mcp add jupyter -- uvx --from jupyter-server-mcp jupyter-server-mcp-proxy

Alternatively, for a single server on a fixed port, connect directly over HTTP:

claude mcp add --transport http jupyter http://localhost:3001/mcp

See the jupyter-server-mcp README for tool registration via jupyter_config.py and snippets for other MCP clients.

BSD-3-Clause