Skip to content
superPDF

JSON results

Inspect schemas and document-operation results.

Runs on your computer. Files stay on your device; the agent or script can only use the folders you allow.

Every superPDF MCP tool declares input and output schemas. Results come back as structured JSON, and new files as links the agent can open, never as raw bytes.

Results

Tool result · pdf_merge
{
  "structuredContent": {
    "output": "/Users/<you>/Documents/superPDF/combined.pdf",
    "pages": 5,
    "bytes": 48213
  },
  "content": [
    { "type": "text", "text": "(the same JSON, for agents that read text)" },
    {
      "type": "resource_link",
      "uri": "file:///Users/<you>/Documents/superPDF/combined.pdf",
      "name": "combined.pdf",
      "mimeType": "application/pdf"
    }
  ]
}

Paths are absolute on your computer; <you> stands for your user name.

Errors

When a request can't run, the error names the field to fix, so the agent can correct itself:

Tool result · pdf_extract_pages
{
  "isError": true,
  "content": [
    {
      "type": "text",
      "text": "Invalid input. pages: Page ranges must be between 1 and 3."
    }
  ]
}

To try it, connect an agent.