Jupyter MCP server

Read from the package source without running it. The installed server may list more.

• append_execute_cellwrite action

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

• connect_notebook

  Connect to a Notebook and corresponding Kernel. It is the FIRST STEP before using following tools.

• delete_cellwrite action

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

• execute_cellwrite action

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

• execute_temporary_cellwrite action

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

• insert_cellwrite action

  Insert a cell above/below of a anchor index. When inserting many cells, MUST insert them in ascending order of their index.

• list_cell

  List the basic information of all 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).

• list_notebook

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

• overwrite_cell

  Overwrite the content of a specific cell

• read_cell

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

• read_notebook

  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.

• restart_notebook

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

• Code scan8 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 335 days ago4/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

75/100

higher than 45% of 48,255 servers

Tools

12

the typical server has 7

Tools that change things

42%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

9

more than 87% of 28,688 servers

Downloads a week

84

more than 59% of 12,191 servers with a package

Jupyter: common questions

Is Jupyter MCP server safe?

Mostly: it is graded B (75/100). Read the Jupyter safety report

How do I install Jupyter?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Jupyter need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Jupyter maintained?

The last commit was 368 days ago (2025-11-01). The latest release is v1.1.0.

How does Jupyter compare with other MCP servers?

safety score 75/100 (higher than 45% of 48,255 servers); tools 12 (the typical server has 7); tools that change things 42% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.