Website Screenshot & PDF for AI Agents avatar

Website Screenshot & PDF for AI Agents

Pricing

Pay per event

Go to Apify Store
Website Screenshot & PDF for AI Agents

Website Screenshot & PDF for AI Agents

Use this when an AI agent needs a clean screenshot or PDF of a web page (cookie banners, ads, chats removed). $0.0015/screenshot, $0.003/full page, $0.005/PDF. Input: {"url":"https://example.com"}. Output: screenshotUrl, title, status, width, height. Fast single-page runs.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Isaac

Isaac

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

11 days ago

Last modified

Security

Limited permissions

Share

Website Screenshot & PDF for AI Agents: Clean Captures, No Cookie Banners

Use this when an AI agent, LLM workflow or script needs to see a web page. Give it a URL and it returns a clean PNG, JPEG, WebP screenshot or a PDF, with cookie banners, GDPR consent pop-ups, ads and chat bubbles removed. You get a public screenshotUrl that your agent can pass to a vision model, attach to a report or store.

This is a lightweight copy of the Website Screenshot & PDF API, built for agent tool calls. It uses the same capture engine and prices but runs as a normal Actor (no Standby). The input is a single url, the defaults are tuned so one capture finishes in about 10–20 seconds, and pricing is fixed per item so agents can predict costs.

Use in ChatGPT or Claude

Add this tool to your AI assistant as a custom connector (MCP server) with this URL:

https://mcp.apify.com?tools=poised_beardlichen/website-screenshot-pdf-agent
  • ChatGPT: Settings → Apps & Connectors → Create (needs Developer mode), paste the URL, choose OAuth and sign in to Apify.
  • Claude: Settings → Connectors → Add custom connector, paste the URL, then click Connect.

Runs go on your own Apify account at the same per-event prices, so the free plan's monthly credit applies.

Try it free

Apify's free plan includes $5 of usage every month, no credit card. On this Actor that's about 3,300 screenshots or 1,000 PDFs a month, so you can test it on your real data before paying anything.

Pricing

Pay per successful capture. There's no start fee or subscription, and platform usage is included:

EventPrice
Viewport screenshot (PNG / JPEG / WebP, any device)$0.0015
Full-page screenshot$0.003
PDF of a page$0.005

Pages that are blocked, return errors or fail to load are not charged. 1,000 screenshots cost $1.50.

Input

Only url is needed:

{ "url": "https://example.com" }

Common options:

  • format: png (default), jpeg, webp or pdf
  • fullPage: true captures the whole scrollable page
  • device: desktop (default), laptop, tablet, mobile or android
  • urls: a list of pages for batches

Advanced options are grouped and optional: custom viewport, retina, dark mode, a CSS selector for one element, wait conditions, custom CSS/JS and proxy.

Output

One dataset item per capture:

{
"url": "https://example.com",
"success": true,
"screenshotUrl": "https://api.apify.com/v2/key-value-stores/.../records/screenshot-example-com-desktop-1a2b3c4d5e.png",
"title": "Example Domain",
"status": 200,
"width": 1920, "height": 1080,
"device": "desktop", "format": "png",
"durationMs": 2100, "error": null
}

When a site refuses the request (captcha or bot protection), the item has success: false and blocked: true, and it isn't charged.

Use with AI agents (MCP)

Add the Actor to Claude Desktop, Cursor, VS Code or any MCP client through the Apify MCP server:

{
"mcpServers": {
"apify": {
"url": "https://mcp.apify.com/?tools=poised_beardlichen/website-screenshot-pdf-agent",
"headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
}
}
}

Then ask: "Take a mobile screenshot of example.com and describe the hero section."

Calling it from an AI agent or a script (async pattern)

A single default screenshot usually finishes in about 10–20 seconds. The Apify MCP server waits only about 30–45 seconds for a run before it returns. So for batches, slow pages, or whenever a call returns before the run is done, start the run and fetch the results afterwards rather than waiting on it:

  1. Start the run: POST https://api.apify.com/v2/acts/poised_beardlichen~website-screenshot-pdf-agent/runs with input such as {"url": "https://example.com"}. The response contains data.id (the run ID) and data.defaultDatasetId.
  2. Wait for it to finish: poll GET https://api.apify.com/v2/actor-runs/<runId>?waitForFinish=60 until status is SUCCEEDED.
  3. Fetch the results: GET https://api.apify.com/v2/datasets/<defaultDatasetId>/items?clean=true.

Send your token as Authorization: Bearer <APIFY_TOKEN>. Through MCP, if the call returns a run ID instead of results, use the server's run-status and dataset tools (e.g. get-actor-run, then get-dataset-items) with that ID. For small, quick jobs you can use the synchronous endpoint POST /v2/acts/poised_beardlichen~website-screenshot-pdf-agent/run-sync-get-dataset-items instead, which waits for up to 300 seconds.

FAQ

How is this different from Website Screenshot & PDF API? The capture engine and prices are the same. The original also offers a real-time HTTP endpoint (Standby mode) for apps. This copy is a plain Actor with an agent-friendly description and defaults.

Does it bypass logins or paywalls? No. It only captures publicly reachable pages.

What if a site blocks it? Set proxyConfiguration to Apify Proxy (residential). Blocked pages are flagged and not charged.

Other tools by us

More agent tools from Monie Tools