procleaning-mcp

Python MCP Server for PDF OCR batch processing.

Features

• Batch OCR - Process multiple PDF files and save results as Markdown
• Single File OCR - Process a single PDF file directly

Tool

batch_ocr_pdf

OCR process PDF file(s) using the OCR API. Supports both single file and directory modes.

Parameters:

• input_file: Path to a single PDF file to process (mutually exclusive with input_dir)
• input_dir: Directory containing PDF files to process (mutually exclusive with input_file)
• output_dir: Directory to save Markdown results (auto-created if not provided)
• api_key: OCR API key (optional, reads from OCR_API_KEY env var)
• base_url: OCR API base URL (default: https://agent.imqimacau.com)

Usage Modes:

1. Single File Mode: Provide input_file only

   input_file: /path/to/document.pdf
   

2. Batch Mode: Provide input_dir only

   input_dir: /path/to/pdf_directory
   

Note: input_file and input_dir are mutually exclusive. At least one must be provided.

Returns: JSON with processing results (success/fail counts per file)

Setup

cd procleaning-mcp
uv sync
uv run python -m procleaning_mcp.server

Usage in Hermes

Add to ~/.hermes/config.yaml:

mcp_servers:
  procleaning:
    command: "uv"
    args: ["run", "--project", "/home/tony/procleaning-mcp", "python", "-m", "procleaning_mcp.server"]
    timeout: 300

Then use mcp_procleaning_batch_ocr_pdf in any Hermes conversation.