pip install mcp PyMuPDF

python server.py

{
  "mcpServers": {
    "pdf-document": {
      "command": "python",
      "args": ["/path/to/pdf-document-mcp/server.py"]
    }
  }
}

Tool: extract_text_from_pdf
Input: {"file_path": "/Users/me/documents/report.pdf"}
Output: {"total_pages": 12, "total_characters": 48320, "pages": [{"page": 1, "text": "...", "char_count": 4210}, ...]}

Tool: extract_text_from_pdf
Input: {"file_path": "/Users/me/documents/report.pdf", "pages": [1, 3, 5]}
Output: {"extracted_pages": 3, "pages": [...]}

Tool: convert_pdf_to_markdown
Input: {"file_path": "/Users/me/documents/whitepaper.pdf"}
Output: {"markdown": "# whitepaper.pdf\n\n---\n## Page 1\n\n### Introduction\n\nThis paper presents...", "char_count": 15200}

Tool: extract_tables
Input: {"file_path": "/Users/me/documents/financials.pdf", "page_num": 3}
Output: {"tables_found": 2, "tables": [{"header": ["Quarter", "Revenue", "Profit"], "rows": [["Q1", "$1.2M", "$400K"], ...]}]}

Tool: merge_pdfs
Input: {"file_paths": ["/tmp/part1.pdf", "/tmp/part2.pdf", "/tmp/part3.pdf"], "output_path": "/tmp/combined.pdf"}
Output: {"output": "/tmp/combined.pdf", "total_pages": 28}

Tool: summarize_document
Input: {"file_path": "/Users/me/documents/thesis.pdf"}
Output: {"statistics": {"total_pages": 45, "total_words": 12500, "total_images": 8}, "headings": [...], "metadata": {"author": "...", "title": "..."}}