# Refinery MCP (npm · @larelabs/refinery-mcp)

Clean raw HTML into LLM-ready text before agents spend tokens.

- Trust score: 65/100 (medium)
- Change this week: +46
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- npm · `@larelabs/refinery-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp.md), [page](https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp)

## Channel facts

- Registry: `npm`
- Package: `@larelabs/refinery-mcp`
- Version: `0.1.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-07.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 147 of 148 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 147 of 148 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 40 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 164 tokens (~54/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add larelabs-refinery-mcp -- npx -y @larelabs/refinery-mcp
```

### Codex

```bash
codex mcp add larelabs-refinery-mcp -- npx -y @larelabs/refinery-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "larelabs-refinery-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@larelabs/refinery-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add larelabs-refinery-mcp --command npx --arg -y --arg @larelabs/refinery-mcp
```

### Hermes

```yaml
mcp_servers:
  larelabs-refinery-mcp:
    command: "npx"
    args: ["-y", "@larelabs/refinery-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "larelabs-refinery-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@larelabs/refinery-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-07 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-06 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-03 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 62, +43)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: MIT

### 2026-07-31 (score 19, +12)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 7, −37)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (3)

### `clean_url` (~57 tokens)

Fetch a URL with the Refinery Apify actor and return clean LLM-ready text plus word_count.

Input parameters:

- `removeScripts` (boolean)
- `removeStyles` (boolean)
- `url` (string, required): The public URL to clean.

### `clean_html` (~54 tokens)

Clean raw HTML that your agent, crawler, or browser session already fetched.

Input parameters:

- `extractHashtags` (boolean)
- `extractMentions` (boolean)
- `html` (string, required): Raw HTML to strip and normalize.

### `estimate_savings` (~53 tokens)

Estimate token savings from raw HTML vs cleaned text without making an Apify call.

Input parameters:

- `cleaned` (string, required): Cleaned text to compare against raw input.
- `raw` (string, required): Original raw HTML or noisy text.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp#diagnostics

## Score history

- 2026-08-07: 65
- 2026-08-06: 64
- 2026-08-05: 63
- 2026-08-04: 63
- 2026-08-03: 63
- 2026-08-02: 62
- 2026-08-01: 19
- 2026-07-31: 19
- 2026-07-30: 7
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/@larelabs/refinery-mcp
- Socket report: https://socket.dev/npm/package/@larelabs/refinery-mcp
- Repository: https://github.com/LareLabs/refinery-mcp
- Changelog RSS feed: https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp.json
- HTML version of this page: https://verifymcp.io/servers/larelabs-refinery-mcp/larelabs-refinery-mcp