Skip to main content
Glama
ChengJiale150

Jupyter MCP Server

by ChengJiale150
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ALLOW_IMGNoWhether to allow returning images as base64; set to 'true' to enable.true

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

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
connect_notebookA

Connect to a notebook and corresponding kernel. It is the FIRST STEP before ANY subsequent operations.

list_notebookA

List all currently connected Notebooks. It will return unique name, Jupyter URL and Path of all connected Notebooks

restart_notebookA

Restart the kernel of a specified Notebook, clear all imported packages and variables

read_notebookA

Read the source content (without output) of a connected Notebook. It will return the formatted content of the Notebook (including Index, Cell Type, Execution Count and Full Source Content). ONLY used when the user explicitly instructs to read the full content of the Notebook.

list_cellA

List the basic information of cells. It will return Index, Type, Execution Count and First Line of the Cell. It will be used to quickly overview the structure and current status of the Notebook or locate the index of specific cells for following operations(e.g. delete, insert).

read_cellB

Read the detailed content of a specific cell. It will return the source code, execution count and output of the cell.

delete_cellA

Delete a specific cell. When deleting many cells, MUST delete them in descending order of their index.

insert_cellB

Insert a cell at the specified index. When inserting many cells, MUST insert them in ascending order of their index.

execute_cellC

Execute a specific cell with a timeout. It will return the output of the cell.

overwrite_cellB

Overwrite the content of a specific cell It will return a comparison (diff style, + for new lines, - for deleted lines) of the cell's content.

append_execute_code_cellA

Add a new code cell to the end of a Notebook and immediately execute it. It is highly recommended for replacing the combination of insert_cell and execute_cell for a code cell at the end of the Notebook. It will return the output of the cell.

execute_temporary_codeA

Execute a temporary code block (not saved to the Notebook) and will return the output.

It will recommend to use in following cases:

  1. Execute Jupyter magic commands(e.g., %timeit, %pip install xxx)

  2. Debug code

  3. View intermediate variable values(e.g., print(xxx), df.head())

  4. Perform temporary statistical calculations(e.g., np.mean(df['xxx']))

DO NOT USE IN THE FOLLOWING CASES:

  1. Import new modules and perform variable assignments that affect subsequent Notebook execution

  2. Run code that requires a long time to run

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 12 tools

Disambiguation5/5

Each tool has a clearly distinct purpose. For example, append_execute_code_cell versus execute_cell differ in that one creates a new cell before executing, while execute_cell runs an existing one. execute_temporary_code is separate for temporary code. All other tools operate on different aspects (connect, list, read, write, delete, etc.), leaving no ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case, such as connect_notebook, list_cell, overwrite_cell, restart_notebook. The compound verb in append_execute_code_cell is still systematic and matches the pattern.

Tool Count5/5

With 12 tools, the set is well-scoped for a Jupyter notebook interaction server. Each tool serves a distinct operation (connect, list, read, write, execute, etc.) without unnecessary duplication or excessive granularity.

Completeness4/5

The tools cover core workflows: connecting, listing, reading, executing, inserting, deleting, overwriting cells, and restarting kernels. Minor gaps exist, such as no explicit save tool or ability to create a new notebook, but these are non-critical for typical agent interactions.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources