MCP Server Box

Extract structured data from one or more files and return a SINGLE metadata instance (Enhanced version).

This enhanced tool analyzes the provided file(s) and extracts information to populate a single metadata instance based on the specified template. When multiple files are provided, Box AI combines information from ALL files to create ONE complete metadata record.

Enhanced features:

• Uses advanced AI models (e.g., Google Gemini) for improved accuracy

• Better handling of complex document layouts and image quality

• More robust extraction for handwritten or low-quality scans

Use cases:

• Single file: Extract metadata from one receipt, invoice, or document

• Multiple files: Combine data from multiple sources into one metadata instance (e.g., extract project info from a proposal PDF, budget spreadsheet, and timeline image)

NOT for batch processing: If you need to extract metadata from multiple files as separate instances, call this tool once per file in a loop.

Args: ctx (Context): The context object containing the request and lifespan context. file_ids (List[str]): The IDs of the files to read. template_key (str): The key of the metadata template to use for the extraction. Example: "insurance_policy_template". Returns: dict: The extracted structured data in a json string format.