工具 API

get_document_image

Retrieve an image from a document — pass an `image_path` from a `get_page_content()` response: either an embedded image (from a content block) or a full rendered page (from the `page_images` array, useful when a page is scanned or its meaning depends on visual layout). Returns the image as an MCP image content block (base64 data + MIME type). Do NOT repeat the raw base64 value in your text response.

devOAuth1 积分

调用信息

工具标识: pageindex-mcp.get_document_image
服务提供方: PageIndex
平均响应: 0 ms
近 7 天调用: 0

输入参数

image_path必填

An image_path from a get_page_content() response, passed back exactly as returned — never constructed or modified. Two sources: an embedded image_path (or img_path) on a content block, or a full-page image_path from the page_images array (format "<doc_name>/_page_images/page-<N>.jpg").

folder_id

Disambiguator when the document name inside image_path is not unique (e.g. two documents in different folders share the same name). Copy the `folder_id` of the intended document from a browse/search result; use "root" for root-level documents, or "shared-with-me"/"following" to pin one of the read-only library-root folders; omit if the name is unique. Copy any folder_id verbatim from a browse_documents()/get_folder_structure() response, never construct one.