Skip to main content
Glama
shwetalsoni

Jupyter Notebook MCP Server

by shwetalsoni
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

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

Tools

Functions exposed to the LLM to take actions

NameDescription
read_notebook_cellsA
Read cells from a Jupyter notebook.

Args:
    notebook_path: Absolute path to the .ipynb file
    cell_type: Optional filter by cell type ('code', 'markdown', 'raw')

Returns:
    List of cell dictionaries with metadata
add_cell_to_notebookA
Add a new cell to a Jupyter notebook.

Args:
    notebook_path: Absolute path to the .ipynb file
    cell_content: Content of the new cell
    cell_type: Type of cell ('code', 'markdown', 'raw')
    position: Position to insert cell (default: append to end)
    metadata: Optional cell metadata

Returns:
    Status of the operation
execute_notebook_cellA
Execute a specific cell in a Jupyter notebook.

Args:
    notebook_path: Absolute path to the .ipynb file
    cell_index: Index of the cell to execute (0-based)
    kernel_name: Jupyter kernel to use for execution
    timeout: Execution timeout in seconds

Returns:
    Execution result with outputs
execute_entire_notebookA
Execute all code cells in a Jupyter notebook sequentially.

Args:
    notebook_path: Absolute path to the .ipynb file
    kernel_name: Jupyter kernel to use for execution
    timeout_per_cell: Timeout per cell in seconds
    stop_on_error: Whether to stop execution if a cell fails

Returns:
    Execution summary with results for each cell
get_notebook_infoB
Get basic information about a Jupyter notebook.

Args:
    notebook_path: Absolute path to the .ipynb file

Returns:
    Notebook metadata and statistics

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 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: adding cells, executing entire notebook, executing a specific cell, getting notebook info, and reading cells. No overlap exists.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case, such as add_cell_to_notebook, execute_entire_notebook, and read_notebook_cells.

Tool Count4/5

With 5 tools, the server is slightly underpopulated but still reasonable for focused notebook operations. The scope feels appropriate without being too thin.

Completeness3/5

The set covers adding, reading, and executing cells but is missing essential operations like creating or deleting notebooks and deleting cells, leaving notable gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources