jupyter-kernel-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| connect_to_jupyterC | Connect to a Jupyter kernel. Starts one if not already running. |
| use_notebookC | Open or create a notebook file and attach it to the session. |
| read_notebookB | List all cells in the open notebook with optional detailed content. |
| read_cellA | Read a single cell by index with its outputs. |
| insert_cellB | Insert a new code or markdown cell at the given index. |
| edit_cell_sourceC | Find and replace text in a cell's source code. |
| delete_cellC | Delete a cell by index. |
| execute_cellC | Execute a code cell in the open notebook and save results. |
| execute_codeA | Execute arbitrary Python code directly (outside the notebook context). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Tools have mostly distinct purposes, but 'execute_cell' and 'execute_code' could confuse agents due to similar names despite different contexts. Other tools are clearly separated.
Most tools follow a verb_noun pattern (e.g., delete_cell, insert_cell), but 'connect_to_jupyter' and 'edit_cell_source' deviate slightly. Overall consistent.
9 tools is well-scoped for a Jupyter kernel server, covering connection, notebook management, cell operations, and code execution without excess.
Covers core CRUD for cells and execution, but missing kernel management tools like restart or interrupt, and no explicit save/close functionality.