Loading...
JupyterMCP allows Claude AI to interact with and control Jupyter Notebook 6.x for AI-assisted code execution, data analysis, and visualization.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
JupyterMCP allows Claude AI to interact with and control Jupyter Notebook 6.x for AI-assisted code execution, data analysis, and visualization.
JupyterMCP offers powerful integration but poses significant risks due to its ability to execute arbitrary code without sandboxing. It's safe for controlled environments with trusted code, but risky when used with untrusted sources or without careful oversight.
Performance is limited by the single-threaded nature of the Jupyter Notebook server and the WebSocket communication overhead. Complex operations or large datasets may result in delays.
The primary cost is the computational resources required to run the Jupyter Notebook server and execute code. Claude API usage may incur additional costs depending on the complexity of the prompts and the amount of data processed.
brew install uv{
"mcpServers": {
"jupyter": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/REPO/FOLDER/src",
"run",
"jupyter_mcp_server.py"
]
}
}
}pingChecks the connectivity to the Jupyter Notebook server.
Read-only operation with no side effects.
insert_and_execute_cellInserts a new cell at a specified position and executes its content.
Allows arbitrary code execution, potentially leading to data modification or deletion.
save_notebookSaves the current Jupyter Notebook.
Modifies the notebook file, potentially overwriting existing content.
get_cells_infoRetrieves information about all cells in the notebook.
Read-only operation that retrieves cell metadata.
get_notebook_infoRetrieves information about the current notebook.
Read-only operation that retrieves notebook metadata.
run_cellRuns a specific cell by its index.
Executes arbitrary code within a specific cell.
run_all_cellsRuns all cells in the notebook sequentially.
Executes arbitrary code in all cells, potentially causing widespread changes.
get_cell_text_outputRetrieves the text output content of a specific cell.
Read-only operation that retrieves cell output.
get_image_outputRetrieves the images output of a specific cell.
Read-only operation that retrieves image output.
edit_cell_contentEdits the content of an existing cell.
Modifies the content of a cell, potentially altering code or markdown.
set_slideshow_typeSets the slide show type for a cell.
Modifies cell metadata related to slideshow presentation.
None
cloud
JupyterMCP offers powerful integration but poses significant risks due to its ability to execute arbitrary code without sandboxing. It's safe for controlled environments with trusted code, but risky when used with untrusted sources or without careful oversight.
Full read/write/execute access is granted by default, with no sandboxing or rollback mechanisms. Exercise extreme caution when using this tool with autonomous agents.
Production Tip
Isolate the Jupyter Notebook server in a dedicated environment with limited access to sensitive resources to mitigate potential risks.
Only Jupyter Notebook version 6.x is supported. Jupyter Lab and Notebook 7.x are NOT compatible.
No, this tool executes arbitrary Python code without sandboxing, which poses a significant security risk. Use only with trusted code sources.
Yes, if the Jupyter Notebook server has access to sensitive data, this tool can potentially access it. Exercise extreme caution and ensure proper security measures are in place.
The client includes a reconnection mechanism, but data loss may occur if a cell was being executed during the disconnection. Consider restarting the WebSocket server.
Isolate the Jupyter Notebook server in a dedicated environment with limited access to sensitive resources. Regularly back up your important projects and data.
No, advanced Jupyter widget interactions are not supported.
No, Google Colab is not supported.