Skip to content
mcp/harbor
Grok

ClicheFactory Document Intelligence for Grok

io.github.clichefactory/clichefactory-mcp

Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.

client:Grok transport:stdio runtime:pypi

Install ClicheFactory Document Intelligence in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "clichefactory-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "clichefactory-mcp"
      ],
      "env": {
        "CLICHEFACTORY_API_KEY": "<CLICHEFACTORY_API_KEY>",
        "CLICHEFACTORY_API_URL": "<CLICHEFACTORY_API_URL>",
        "LLM_MODEL_NAME": "<LLM_MODEL_NAME>",
        "LLM_API_KEY": "<LLM_API_KEY>",
        "OCR_MODEL_NAME": "<OCR_MODEL_NAME>",
        "OCR_API_KEY": "<OCR_API_KEY>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

ClicheFactory Document Intelligence in other clients

ClicheFactory Document Intelligence MCP server