MCPLow riskUnclaimed

Refinery MCP

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

LareLabslarelabs/refinery-mcpUpdated Jun 28, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.LareLabs/refinery-mcp",
  "description": "Clean raw HTML into LLM-ready text before agents spend tokens.",
  "title": "Refinery MCP",
  "repository": {
    "url": "https://github.com/LareLabs/refinery-mcp",
    "source": "github"
  },
  "version": "0.1.6",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@larelabs/refinery-mcp",
      "version": "0.1.6",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Apify API token for the Refinery HTML cleaner actor",
          "isRequired": true,
          "format": "string",
          "isSecret": true,
          "name": "APIFY_TOKEN"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@larelabs/refinery-mcp@0.1.6
Runs install scripts—None
NetworkNoneNone
Needs credentialsAPIFY_TOKENAPIFY_TOKEN
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.6latestOct 7, 2026