# caveman-core-mcp

> caveman-core-mcp — matheuspcardoso-caveman-mcp. Use this tool when you need to simplify complex language model responses while preserving technical accuracy, reducing token usage by approximately 65%. It takes in LLM responses as input and outputs condensed, caveman-style prose, making it ideal for applications where concise language is essential. This tool is particularly useful in contexts where token efficiency is crucial, such as in low-bandwidth or cost-sensitive environments.

Canonical page: https://skillsregistry.net/skills/matheuspcardoso-caveman-mcp  
JSON: https://api.skillsregistry.net/v1/skills/matheuspcardoso-caveman-mcp

## Description

MCP server that compresses LLM responses into caveman-style prose, reducing token usage by ~65% while maintaining technical accuracy.

## 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/vnhx0a3thb)
- **Repository:** <https://github.com/MatheusPCardoso/caveman-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": "matheuspcardoso-caveman-mcp"
    }
  }
}
```

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