# Jupyter Kernel State

> Use this tool when you need to bridge AI coding agents with Jupyter kernels to access live variable values, dataframe summaries, and plot captures. It solves problems of kernel introspection and cell operations, providing a more comprehensive interface than traditional Jupyter servers. Ideal for use cases requiring dynamic interaction with Jupyter notebooks, it accepts kernel connections and outputs introspection data, supporting both server and standalone modes.

Canonical page: https://skillsregistry.net/skills/bettyguo-mcp-jupyter  
JSON: https://api.skillsregistry.net/v1/skills/bettyguo-mcp-jupyter

## Description

Bridges AI coding agents with running Jupyter kernels, surfacing live variable values, dataframe summaries, recent cells, traceback information, and base64-encoded plot captures rather than raw notebook JSON. Provides approximately ten tools for kernel introspection and cell operations, filling the gap left by cell-operation-only Jupyter MCP servers. Supports two modes: server mode (connects to an existing Jupyter instance) and standalone mode (spawns its own kernel). Implemented in Python; pre-alpha and installed from source.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/bettyguo-mcp-jupyter)
- **Repository:** <https://github.com/bettyguo/mcp-jupyter>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "bettyguo-mcp-jupyter"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bettyguo-mcp-jupyter` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bettyguo-mcp-jupyter/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt