# scratchbook-mcp

> scratchbook-mcp — jinyaolin-scratchbook. Use this tool when you need to efficiently search and manage codebases, solve complex coding problems, and track progress through a work journal. It provides hybrid semantic and BM25 code search, structural outlines, and deep reasoning capabilities over a local database. Ideal for AI coding agents requiring advanced code analysis and organization in a general development context.

Canonical page: https://skillsregistry.net/skills/jinyaolin-scratchbook  
JSON: https://api.skillsregistry.net/v1/skills/jinyaolin-scratchbook

## Description

A codebase-memory MCP server for AI coding agents with hybrid semantic+BM25 code search, structural outlines, a work journal, and gaze-and-think deep reasoning over a local LanceDB database.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cumjd77u33)
- **Repository:** <https://github.com/jinyaolin/scratchbook>

## 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": "jinyaolin-scratchbook"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jinyaolin-scratchbook` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jinyaolin-scratchbook/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