pdf_replace_text

Instructions

Implementation Reference

• pdf_manipulation_mcp_server/pdf_server.py:94-158 (handler)

  The primary handler function for the 'pdf_replace_text' tool. Decorated with @mcp.tool() for automatic registration in FastMCP. It validates the input PDF, searches for instances of old_text on the specified page or all pages, replaces them by redacting the old text and inserting the new text using PyMuPDF (fitz), generates a timestamped output filename, and saves the modified PDF.

  @mcp.tool()
  async def pdf_replace_text(
      pdf_path: str,
      old_text: str,
      new_text: str,
      page_number: Optional[int] = None
  ) -> str:
      """Replace text in a PDF document."""
      if not os.path.exists(pdf_path):
          return f"Error: PDF file not found: {pdf_path}"
      
      if not validate_pdf_file(pdf_path):
          return f"Error: Invalid PDF file: {pdf_path}"
      
      try:
          # Open PDF document
          doc = fitz.open(pdf_path)
          
          # Determine pages to search
          pages_to_search = [page_number] if page_number is not None else range(len(doc))
          
          # Validate page number if specified
          if page_number is not None and not validate_page_number(doc, page_number):
              doc.close()
              return f"Error: Invalid page number {page_number}. Document has {len(doc)} pages."
          
          replacements_made = 0
          
          # Search and replace text
          for page_num in pages_to_search:
              page = doc[page_num]
              
              # Search for the text
              text_instances = page.search_for(old_text)
              
              if text_instances:
                  # Use redaction to replace text
                  for rect in text_instances:
                      # Add redaction annotation
                      redact = page.add_redact_annot(rect, fill=(1, 1, 1))  # White fill
                      page.apply_redactions()
                      
                      # Insert new text at the same position
                      page.insert_text(
                          (rect.x0, rect.y1),  # Position at bottom-left of original text
                          new_text,
                          fontsize=12
                      )
                      replacements_made += 1
          
          if replacements_made == 0:
              doc.close()
              return f"No instances of '{old_text}' found in the PDF."
          
          # Generate output filename
          output_path = generate_output_filename(pdf_path)
          
          # Save the modified PDF
          doc.save(output_path)
          doc.close()
          
          return f"Successfully replaced {replacements_made} instances of text. Output saved to: {output_path}"
          
      except Exception as e:
          return f"Error replacing text in PDF: {str(e)}"

• pdf_manipulation_mcp_server/pdf_server.py:28-36 (helper)

  Helper function used by pdf_replace_text to validate that the input file is a valid PDF by attempting to open it with PyMuPDF.

  def validate_pdf_file(pdf_path: str) -> bool:
      """Validate that the file is a valid PDF."""
      try:
          doc = fitz.open(pdf_path)
          doc.close()
          return True
      except Exception:
          return False

• pdf_manipulation_mcp_server/pdf_server.py:22-27 (helper)

  Helper function used by pdf_replace_text to generate a timestamped output filename to avoid overwriting the original PDF.

  def generate_output_filename(input_path: str, suffix: str = "modified") -> str:
      """Generate a new filename with timestamp to avoid overwriting originals."""
      path = Path(input_path)
      timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
      return str(path.parent / f"{path.stem}_{suffix}_{timestamp}{path.suffix}")

• pdf_manipulation_mcp_server/pdf_server.py:37-40 (helper)

  Helper function used by pdf_replace_text to validate the optional page_number input.

  def validate_page_number(doc: fitz.Document, page_num: int) -> bool:
      """Validate that the page number exists in the document."""
      return 0 <= page_num < len(doc)