# kernel-mcp

> kernel-mcp — luckylobster8868-kernel-mcp. Use this tool when you need to execute code in a stateful Python environment, inspect variables and dataframes, or optimize SQL queries. It provides a persistent Jupyter kernel for interactive coding and debugging, allowing agents to work with dynamic data and iterative processes. Ideal for data science, scientific computing, and machine learning tasks that require iterative development and testing.

Canonical page: https://skillsregistry.net/skills/luckylobster8868-kernel-mcp  
JSON: https://api.skillsregistry.net/v1/skills/luckylobster8868-kernel-mcp

## Description

Provides a persistent Jupyter kernel for executing code, inspecting variables and dataframes, and checking SQL query plans, enabling agents to work with stateful Python sessions.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a4ntbf3vd4)
- **Repository:** <https://github.com/Luckylobster8868/kernel-mcp>

## 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": "luckylobster8868-kernel-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/luckylobster8868-kernel-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/luckylobster8868-kernel-mcp/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