# scratch-mcp

> Use this tool when you need to create and execute Scratch projects programmatically, solving problems such as automating Scratch development and testing. It takes plain text input and outputs compiled Scratch projects, utilizing a live editor loop for iterative development. Ideal for AI agents requiring dynamic Scratch project creation and execution in various educational or prototyping contexts.

Canonical page: https://skillsregistry.net/skills/fromarkzoo-scratch-mcp  
JSON: https://api.skillsregistry.net/v1/skills/fromarkzoo-scratch-mcp

## Description

Enables AI agents to create, compile, and run Scratch projects by editing plain text and using a live editor loop.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rxouvsecgi)
- **Repository:** <https://github.com/FromArkZoo/scratch-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": "fromarkzoo-scratch-mcp"
    }
  }
}
```

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