# refinery-mcp

> refinery-mcp — larelabs-refinery-mcp. Use this tool when you need to preprocess HTML data for AI agents, as it cleans and refines HTML from URLs or raw HTML into LLM-ready text, reducing token burn and improving efficiency. It takes in HTML URLs or raw HTML as input and outputs cleaned text, making it ideal for use cases where HTML data needs to be processed for language models. This tool is particularly useful when working with web-scraped data or HTML-rich text that requires refinement for AI analysis.

Canonical page: https://skillsregistry.net/skills/larelabs-refinery-mcp  
JSON: https://api.skillsregistry.net/v1/skills/larelabs-refinery-mcp

## Description

Cleans HTML from URLs or raw HTML into LLM-ready text, reducing token burn for AI agents.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nlfdx7hvw8)
- **Repository:** <https://github.com/LareLabs/refinery-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": "larelabs-refinery-mcp"
    }
  }
}
```

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