# toon-mcp

> Use this tool when you need to optimize LLM prompts by reducing token usage, as it enables encoding JSON into compact TOON format and decoding TOON back to JSON. It solves the problem of excessive token consumption in large JSON prompts, making it ideal for use cases with limited token budgets. The tool takes JSON or TOON as input and outputs the corresponding compact TOON or original JSON format.

Canonical page: https://skillsregistry.net/skills/kweinmeister-toon-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kweinmeister-toon-mcp

## Description

Enables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kbse40po3l)
- **Repository:** <https://github.com/kweinmeister/toon-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": "kweinmeister-toon-mcp"
    }
  }
}
```

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