This Jupyter MCP server implementation, developed by Datalayer, provides a bridge between the Model Context Protocol (MCP) and Jupyter environments. It leverages Jupyter's kernel and notebook model clients to enable AI assistants to interact with Jupyter notebooks, execute code, and manipulate notebook content. The server is designed to run in a Docker container, making it easily deployable and scalable. It's particularly useful for data scientists and researchers who want to integrate AI-powered tools into their Jupyter workflows, enabling automated analysis, code generation, and interactive data exploration within notebook environments.
まだレビューはありません. 最初のレビューを投稿しましょう！
会話に参加するにはサインインしてください
List files and directories in the Jupyter server's file system.
List all available and running kernel sessions on the Jupyter server.
Connect to a Jupyter server dynamically without restarting the MCP server. Not available when running as Jupyter extension.
Connect to a notebook file, create a new one, or switch between notebooks.
List all notebooks available on the Jupyter server and their status.
Restart the kernel for a specific managed notebook.
Disconnect from a specific notebook and release its resources.
Read notebook cells source content with brief or detailed format options.
Read the full content (Metadata, Source and Outputs) of a single cell.
Insert a new code or markdown cell at a specified position.
Delete a cell at a specified index.
Overwrite the source code of an existing cell.
Execute a cell with timeout, supports multimodal output including images.
Insert a new code cell and execute it in one step.
Execute code directly in the kernel, supports magic commands and shell commands.
Execute all cells in the current notebook sequentially.
Get information about the currently selected cell.
Cite specific cells from specified notebook (like @ in Coding IDE or CLI).
