doc_read

DocumentsRead-only

A document's model: every element (annotations, images, tails...) with all its properties, and its sections (canvas, stage, camera, document), each in the shape doc_edit's set takes. Points and rects are the picture's own pixels (canvas.picture_at says where the picture sits in doc_render's image). With no id, the item open in an editor, else the gallery's current item. describe explains every kind and property.

Available at every access level, including a client that sent X-Access-Level: readonly.

Parameters

Name	Type	Required	Description
id	string	no	The item's id.
path	string	no	Or its path or name.
page	integer	no	A multi-page image's page (1 is the first; default the one on screen).
ids	string[]	no	Only these elements (ids, or section names); with kinds, these as well as those.
kinds	string[]	no	Only elements of these kinds; with ids, these as well as those.
text	boolean	no	Also the words in the picture (read from its pixels), with where each line is.
codes	boolean	no	An image: also the QR codes and barcodes in the picture, decoded (text and format), as Extract QR/Barcode reads them.
at_ms	integer	no	For a video: read each annotation that animates as it is at this moment (default: at its start).
coords	string one of "doc", "render"	no	doc (default): the picture's own pixels (a video item's: the recording's, or the canvas's for a canvas item). render: the pixels of your last doc_render of this document, as you saw it.

Example

A JSON-RPC call to POST http://localhost:21516/mcp with the bearer token, filling in the required parameters:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "doc_read",
    "arguments": {}
  }
}

See the MCP server overview for how to connect a client and where the token lives.