# TOON

> Use this tool when you need to efficiently encode and decode various data formats, such as JSON, CSV, and XML, to reduce token usage by 50-65%. It solves problems of data redundancy and large file sizes by converting data into a compact header-based format. Ideal for use cases involving large datasets, data transfer, and storage, where token reduction can significantly improve performance and efficiency.

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

## Description

TOON (Token-Oriented Object Notation) encodes JSON, CSV, XML, HTML tables, and YAML into a compact header-based format where field names are defined once rather than repeated for each record. The server provides tools for encoding data to TOON format, decoding back to JSON, analyzing potential token savings, and automatically optimizing prompts by detecting and converting embedded data sections. Benchmarks show consistent 50-65% token reduction across datasets of varying sizes.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **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:** [PulseMCP](https://www.pulsemcp.com/servers/elminson-toon)
- **Repository:** <https://github.com/elminson/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": "elminson-toon"
    }
  }
}
```

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