# scratchpad-mcp

> Use this tool when you need to efficiently store and manage data for AI agents, reducing redundant file reads and summaries. It provides persistent storage with features like versioned file writes, line-diffs, and append-only logs, solving problems of data duplication and agent inefficiency. Ideal for use cases where AI agents require token-efficient access to stored data, with inputs including file writes and queries, and outputs including cached summaries and versioned data.

Canonical page: https://skillsregistry.net/skills/mikepressure-scratchpad-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mikepressure-scratchpad-mcp

## Description

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. Eight tools versioned file writes, structured line-diffs since a prior version, append-only logs with cursor pagination, on-demand summaries with per-version caching, and per-agent quotas. The point is to stop agents from re-reading files they've already seen and re-summarizing documents.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jg3ullulkf)
- **Repository:** <https://github.com/MikePressure/scratchpad-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": "mikepressure-scratchpad-mcp"
    }
  }
}
```

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