PDF to Image

Overview

Pages are rendered with Poppler, the PDF engine used by most Linux desktops, so text, vector graphics, images and page rotation come out as a PDF viewer shows them. Very large pages are rendered at a lower dpi so no image exceeds 25 megapixels, and each image reports the dpi it was rendered at. Encrypted PDFs are rejected.

Live Test PDF to Image Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as PDFtoImage. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "PDFtoImage",
  "arguments": {}
}

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`pdf`Optional	string	The PDF file to render (up to 10 MB), or a public PDF URL
`pages`Optional	string	Pages to render, as numbers and ranges such as 1-3,5; at most 10 per call on paid plans, 1 on the Free plan default 1 · length 0–100
`format`Optional	string	Image format `pngjpgjpeg` default png
`quality`Optional	integer	JPG quality from 1 to 100; ignored for PNG default 90 · range 1–100
`dpi`OptionalPremium	integer	Resolution in dots per inch, from 72 to 300 default 150 · range 72–300

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "pageCount": 14,
    "format": "png",
    "dpi": 150,
    "imageCount": 2,
    "expires": 1792400000000,
    "images": [
      {
        "page": 1,
        "imageName": "3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-1.png",
        "width": 1275,
        "height": 1650,
        "dpi": 150,
        "size": 214533,
        "downloadURL": "https://storage.googleapis.com/apiverve/APIData/pdftoimage/3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-1.png?GoogleAccessId=635500398038-compute%40developer.gserviceaccount.com&Expires=1792400000&Signature=SAMPLE"
      },
      {
        "page": 2,
        "imageName": "3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-2.png",
        "width": 1275,
        "height": 1650,
        "dpi": 150,
        "size": 198207,
        "downloadURL": "https://storage.googleapis.com/apiverve/APIData/pdftoimage/3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-2.png?GoogleAccessId=635500398038-compute%40developer.gserviceaccount.com&Expires=1792400000&Signature=SAMPLE"
      }
    ]
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`pageCount`	number	`14`	Total pages in the PDF
`format`	string	`png`	Image format (png or jpg)
`dpi`	number	`150`	Requested resolution in dots per inch
`imageCount`	number	`2`	Number of pages rendered
`expires`	number	`1792400000000`	When the download links expire (Unix time in milliseconds)
`images`	array[2]		One entry per rendered page, in the order requested
`images.0.page`	number	`1`	Page number
`images.0.imageName`	string	`3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-1.png`	File name of the image
`images.0.width`	number	`1275`	Image width in pixels
`images.0.height`	number	`1650`	Image height in pixels
`images.0.dpi`	number	`150`	Resolution the page was rendered at; lower than requested only for very large pages
`images.0.size`	number	`214533`	Image size in bytes
`images.0.downloadURL`	string	`https://storage.googleapis.com/apiverve/APIData/pdftoimage/3b7e9d21-4c5a-4f80-a1d6-9e2c8b7f5a34-1.pn…`	Signed link to download the image, valid for 2 days

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This skill is not part of VerveKit. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 10 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Document Thumbnails: Show a preview image of the first page of uploaded PDFs in file lists and search results.
Page Previews: Display individual pages of a contract or report as images where a PDF viewer is not available.
OCR Pipelines: Turn scanned PDF pages into images for the Image to Text API or another OCR step.
Social and Email Images: Use a page of a brochure, menu or flyer PDF as an image in posts and newsletters.

Other ways to use PDF to Image

Set up PDF to Image on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →