// MCP TOOL REFERENCE

JUPYTER TOOLS

7 tools from the Jupyter MCP Server, categorised by risk level.

READ TOOLS

jupyter_get_notebook Read a Jupyter notebook (.ipynb) file. jupyter_list_kernels List all active Jupyter kernels.

WRITE TOOLS

jupyter_add_cell Add a new cell (code/markdown) to a notebook. 2/5 jupyter_create_notebook Create a new empty Jupyter notebook. 2/5 jupyter_open_notebook Open a notebook in the default browser or viewer. 2/5 jupyter_update_cell Update the content of an existing cell. 2/5

EXECUTE TOOLS

jupyter_execute_code Execute code in a real Jupyter kernel. 3/5

// FAQ

How many tools does the Jupyter MCP server have? +

The Jupyter MCP server exposes 7 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Jupyter tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Jupyter server.

What risk categories do Jupyter tools fall into? +

Jupyter tools are categorised as Read (2), Write (4), Execute (1). Each category has a recommended default policy.

Enforce policies on Jupyter

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →