OfficeReader-MCP

Instructions

Implementation Reference

• src/officereader_mcp/server.py:305-377 (handler)

  Handler implementation for get_document_metadata tool that parses the file_path argument, determines the Office document type, loads the document using appropriate library (docx, openpyxl, or pptx), extracts core properties/metadata, and returns it as JSON.
  elif name == "get_document_metadata": file_path = arguments.get("file_path") if not file_path: return [TextContent( type="text", text=f"{cache_notice}\n\n" + json.dumps({"error": "file_path is required"}, ensure_ascii=False) )] from .converter import get_file_type file_path_obj = Path(file_path) file_type = get_file_type(file_path_obj) metadata = { "file": file_path, "file_type": file_type, "cache_location": str(converter.cache_dir), } if file_type == "word": from docx import Document doc = Document(file_path) core_props = doc.core_properties metadata.update({ "title": core_props.title or "", "author": core_props.author or "", "created": str(core_props.created) if core_props.created else "", "modified": str(core_props.modified) if core_props.modified else "", "last_modified_by": core_props.last_modified_by or "", "subject": core_props.subject or "", "keywords": core_props.keywords or "", "category": core_props.category or "", "comments": core_props.comments or "", "revision": core_props.revision, }) elif file_type == "excel": from openpyxl import load_workbook wb = load_workbook(file_path, data_only=True) props = wb.properties metadata.update({ "title": props.title or "", "creator": props.creator or "", "created": str(props.created) if props.created else "", "modified": str(props.modified) if props.modified else "", "sheet_count": len(wb.sheetnames), "sheet_names": wb.sheetnames, }) elif file_type == "powerpoint": from pptx import Presentation prs = Presentation(file_path) core_props = prs.core_properties metadata.update({ "title": core_props.title or "", "author": core_props.author or "", "created": str(core_props.created) if core_props.created else "", "modified": str(core_props.modified) if core_props.modified else "", "subject": core_props.subject or "", "slide_count": len(prs.slides), }) else: return [TextContent( type="text", text=f"{cache_notice}\n\n" + json.dumps({ "error": f"Unsupported file format: {file_path_obj.suffix}", "supported": get_supported_extensions() }, ensure_ascii=False) )] return [TextContent( type="text", text=f"{cache_notice}\n\n" + json.dumps(metadata, ensure_ascii=False, indent=2) )]
• src/officereader_mcp/server.py:139-157 (registration)

  Registration of the get_document_metadata tool via server.list_tools() decorator, defining the tool name, description, and input schema requiring 'file_path'.
  Tool( name="get_document_metadata", description=f"""Get metadata from an Office document without full conversion. Extracts document properties like title, author, creation date, etc. Faster than full conversion when you only need metadata. Supported formats: {supported_exts}""", inputSchema={ "type": "object", "properties": { "file_path": { "type": "string", "description": f"Absolute path to the Office document. Supported: {supported_exts}", }, }, "required": ["file_path"], }, ),
• src/officereader_mcp/server.py:147-156 (schema)

  Input schema for get_document_metadata tool, defining the required 'file_path' parameter.
  inputSchema={ "type": "object", "properties": { "file_path": { "type": "string", "description": f"Absolute path to the Office document. Supported: {supported_exts}", }, }, "required": ["file_path"], },