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"],
  },