$ loading_
Connect local Jupyter kernels for code execution, kernel management, and notebook runs.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Jupiter Controller MCP" yet — see the docs or source repo.
Connect to a local Jupyter kernel, run this Python code, and return the output: import pandas, read sample.csv, and summarize missing values plus numeric column means.
Returns execution results including missing-value counts, means, and related output details.
List the currently available local Jupyter kernels and explain which one I should use for a Python 3 analysis task.
Returns a list of available kernels and recommends one suitable for the task.
Use a local Jupyter kernel to execute this notebook and capture outputs plus error summaries for each cell.
Returns notebook execution status along with summarized cell outputs or errors.
Developers or researchers can connect a local Jupyter kernel during AI collaboration, run code, and get outputs without switching to a separate notebook environment.
Data analysts working across different project environments can inspect and manage local kernels, then choose the right execution environment for a task.
When notebooks need to be run repeatedly, the tool can trigger notebook execution and capture outputs, helping users review results and errors quickly.
It connects Claude Code to local Jupyter kernels for code execution, kernel management, and notebook execution, with security gating and output capture.
Yes. The original description explicitly mentions notebook execution, so it can run notebooks as well as code snippets.
The provided material does not include installation steps, dependencies, or key requirements. For specifics, see the source repository.
Connect to a Jupyter kernel to manage, edit, and run notebooks.
Connect and manage Jupyter notebooks for interactive coding, analysis, and visualization.
Let AI manage notebook cells, dependencies, and efficient code execution.
Connect to Jupyter via MCP to run code and explore data interactively.
Control a live JupyterLab instance from any MCP-compatible client.
Connect AI agents to control local JupyterLab for coding and analysis.