Built for AI agents & coding assistants

Screenshot API for AI Agents, Claude, Cursor, and ChatGPT

Give your agents a hosted way to capture any public or authorized web page, raw HTML, dashboard, or preview as an image or PDF — no Puppeteer, no Playwright, no browser infrastructure to run.

Works with every major agent, assistant & framework

Start free — 200 screenshots/mo Agent setup guide

No credit card required. Get an API key from your dashboard in seconds.

Drop this into your agent

Paste into your agent

Integrate ScreenshotAPI (https://screenshotapi.to) for screenshots and PDFs.

First, read:
- https://screenshotapi.to/llms-full.txt   # full docs + product facts
- https://screenshotapi.to/openapi.json     # machine-readable API contract

Call the REST API with header:  x-api-key: <my key>
Capture public or authorized URLs only — never localhost,
private networks, or cloud metadata endpoints.

Connect in seconds

Use the production REST API and OpenAPI schema today, or wire up the Model Context Protocol server. Both back the same hosted capture engine.

One authenticated GET request returns a screenshot or PDF. Works in every language, framework, and agent runtime — no SDK required.

cURL

curl "https://screenshotapi.to/api/v1/screenshot?url=https://example.com&type=png&fullPage=true" \
  -H "x-api-key: sk_live_your_key_here" \
  --output screenshot.png

JavaScript

const res = await fetch(
  'https://screenshotapi.to/api/v1/screenshot' +
    '?url=https://example.com&type=png&fullPage=true',
  { headers: { 'x-api-key': process.env.SCREENSHOTAPI_KEY } }
)

if (!res.ok) throw new Error(await res.text())
const image = await res.arrayBuffer()

Set up your agent

Pick your assistant and follow the shortest path. Every option is backed by your ScreenshotAPI key.

ChatGPT & Custom GPTs

Import the OpenAPI schema as a GPT Action and authenticate with your API key. No code required.

OpenAPI schema

Claude (Code & Desktop)

Paste the agent prompt to load the docs, or add the MCP server to your Claude config.

MCP setup

Cursor

Reference llms-full.txt in chat for implementation-ready examples, or register the MCP server.

llms-full.txt

VS Code & Copilot

Point Copilot agent mode at the OpenAPI schema, or add the MCP server in agent mode.

OpenAPI schema

Codex

Add the MCP server to your Codex config, or call the REST API directly from generated code.

MCP setup

Agent frameworks

Wrap the REST API as a tool in LangChain, the Vercel AI SDK, the OpenAI Agents SDK, Pipedream, or Zapier.

Agent guide

What your agents can build

A single capture call unlocks a wide range of agent workflows.

Visual QA evidence

Capture before-and-after screenshots of a page during review, QA, or regression checks.

Link previews & thumbnails

Turn user-submitted URLs into rich previews or directory listing thumbnails.

OG & HTML rendering

Render agent-generated HTML into Open Graph images, email previews, or invoices.

Dashboards & reports

Export dashboards and reports as images or PDFs for agent-written summaries.

Monitoring snapshots

Collect visual change evidence on a schedule for monitoring and alerting flows.

Web archives

Preserve a pixel-accurate snapshot of any public page as an artifact.

Good fit

An agent needs a screenshot of a public or authorized URL.
An agent needs to render raw HTML into an image or PDF.
An agent needs visual evidence before or after a change.
You want hosted infrastructure instead of running Puppeteer or Playwright.

Not a fit

Interactive browser control, form submission, or multi-step login.
Targeting localhost, private networks, cloud metadata, or internal services.
Bypassing paywalls, account access, or consent.
Unbounded agent loops without explicit rate limits and cache TTLs.

Agent workflow guides

Use these when an agent needs a specific capture pattern rather than a general API overview.

URL to Image API for AI Agents

Capture public or authorized URLs as PNG, JPEG, or WebP.

HTML to Image API for AI Agents

Render agent-generated HTML into image artifacts.

URL to PDF API for AI Agents

Generate PDF artifacts from URLs or raw HTML.

Visual QA Evidence for AI Agents

Capture before-and-after screenshots for review and QA.

Machine-readable resources

Point tools, agent context, or actions at these URLs. Every one is live and versioned with the API.

OpenAPI schema

Machine-readable API contract for GPT Actions and tools.

llms.txt

Compact agent-readable index of docs and use cases.

llms-full.txt

Full documentation corpus with a product factsheet.

Agent install guide

Step-by-step setup instructions in agent-readable Markdown.

MCP server card

Tool schema, package names, and auth model for MCP clients.

MCP server page

MCP tools, config, and install surfaces.

Give your agents eyes on the web

Create a free account, grab an API key, and start capturing in minutes. 200 screenshots per month, free.

Create free account