list_sandboxes
List launched code sandboxes and their state (active flag, variant, status, and selected code sandbox options). Requires the jupytermcpsandboxes extension.
How to use it
list_sandboxes is exposed by the Jupyter MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the list_sandboxes tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Jupyter MCP Server
pip install jupyterlab jupyter-collaboration jupyter-mcp-tools ipykernelOther tools in Jupyter MCP Server (23)
Clear the outputs and execution count of a single code cell.
Connect to a Jupyter server dynamically without restarting the MCP server. Not available when running as Jupyter extension. Useful for switching servers dynamically or avoiding hardcoded configuration.
Delete a cell at a specified index.
Apply surgical find-and-replace edits to a cell's source without full rewrite.
Execute a cell with timeout, supports multimodal output including images.
Execute code directly in the active backend (kernel by default, or active sandbox if selected), supports magic commands and shell commands. When the selected sandbox supports streaming execution, progress/output events are consumed and returned in order.
Insert a new code or markdown cell at a specified position.
Insert a new code cell and execute it in one step.
Launch a code sandbox (eval/docker/jupyter/datalayer/kaggle/googlecolab/google-colab/colab/monty/modal) as an alternative execution backend for executecode. Supports variant-specific options including GPU flavor for supported backends. Requires the jupytermcpsandboxes extension.
List files and directories in the Jupyter server's file system.
List all available and running kernel sessions on the Jupyter server.
List all notebooks available on the Jupyter server and their status
Move a cell from one position to another within a notebook.
Get information about the currently selected cell
Execute all cells in the current notebook sequentially
Overwrite the source code of an existing cell.
Read the full content (Metadata, Source and Outputs) of a single cell.
Read notebook cells source content with brief or detailed format options.
Restart the kernel for a specific managed notebook.
Stop and unregister a launched code sandbox. Requires the jupytermcpsandboxes extension.
Disconnect from a specific notebook and release its resources.
Connect to a notebook file, create a new one, or switch between notebooks.
Select or clear the active sandbox used by executecode, enabling dynamic routing between kernel-backed and sandbox-backed execution. Requires the jupytermcpsandboxes extension.