# TokenDiet MCP

> TokenDiet MCP — dukedesouth-tokendiet-mcp. Use this tool when you need to optimize token usage in AI agents by compressing large inputs such as file reads, command outputs, and web pages. TokenDiet MCP reduces token consumption through deterministic transforms, while a safety verifier ensures the integrity of the compressed data. It is ideal for use cases where token limits are a concern, such as large-scale data processing or resource-constrained environments.

Canonical page: https://skillsregistry.net/skills/dukedesouth-tokendiet-mcp  
JSON: https://api.skillsregistry.net/v1/skills/dukedesouth-tokendiet-mcp

## Description

Compresses file reads, command output, search hits, and fetched web pages before entering agent context to reduce token usage, using deterministic transforms and a safety verifier.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/d92lkmhg5y)
- **Repository:** <https://github.com/DukeDeSouth/tokendiet-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": "dukedesouth-tokendiet-mcp"
    }
  }
}
```

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