TOOL API
get_
Extract specific page content from processed documents. Flexible page selection: single page ('5'), ranges ('3-7'), or multiple pages ('1,5,10'). Use tight, targeted ranges and split into multiple calls if needed. Avoid extracting entire documents at once. Optional: wait_for_completion (boolean) to wait up to 3 minutes if still processing. Returns structured text content with image paths. To retrieve embedded images: use the image paths from this response with get_document_image(). For documents over 20 pages, call get_document_structure() first to identify relevant sections. For small documents (20 pages or fewer), call this directly.
Call information
- Tool slug
- pageindex-mcp.get_page_content
- Provider
- PageIndex
- Average response
- 0 ms
- Calls in 7 days
- 0
Input parameters
doc_namerequiredCopy the `name` field verbatim from a browse_documents() or search_documents() response (case-sensitive, include extension). Example: "Q3 Report.pdf". If the response shows two documents with the same name, pass `folder_id` alongside to disambiguate.
folder_idDisambiguator for same-name documents. Copy the `folder_id` from the intended browse/search result; use "root" for root-level documents, or "shared-with-me"/"following" for the read-only folders at the library root; omit if `doc_name` is unique. Copy any folder_id verbatim from a browse_documents()/get_folder_structure() response, never construct one.
pagesrequiredPage specification: "5", "3,7,10", "5-10", or "1-3,7,9-12"
wait_for_completionIf true and document is processing, automatically wait up to 3 minutes until completed. Reduces repeated tool calls.