TOOL API

get_document_structure

Extract the hierarchical structure of a completed document. Optional: wait_for_completion (boolean) to wait up to 3 minutes if still processing. Returns structured outline with headers, sections, and page references. REQUIRED for documents over 20 pages - use this first to understand layout and identify relevant sections before extracting content. For targeted questions, use structure to locate relevant pages, then extract with get_page_content().

devOAuth1 credits

Call information

Tool slug: pageindex-mcp.get_document_structure
Provider: PageIndex
Average response: 0 ms
Calls in 7 days: 0

Input parameters

doc_namerequired

Document name from recent_documents()

folder_id

Filter by folder ID. Use "root" for root folder files, omit to use the default.

part

Part number for pagination (1-based)

wait_for_completion

If true and document is processing, automatically wait up to 3 minutes until completed. Reduces repeated tool calls.