Site-Shot - Screenshot API for AI Agents & MCP Server

Install the MCP server

Add Site-Shot to Claude Desktop, Cursor, Cline, or any MCP client:

{
  "mcpServers": {
    "site-shot": {
      "command": "npx",
      "args": ["-y", "site-shot-mcp"],
      "env": { "SITESHOT_API_KEY": "YOUR_API_KEY" }
    }
  }
}

Then ask your agent to “take a full-page screenshot of example.com” — it gets the image back inline. Two tools: capture_screenshot and capture_full_page.

Why Site-Shot for agents

Fewer vision tokens. Automatic ad + cookie-banner removal (no_ads, no_cookie_popup) means cleaner screenshots and less noise for your vision model to pay for.
Real Chromium. Pages render exactly as a real visitor sees them — JS, fonts, lazy-loaded images.
Full-page capture up to 20,000px, or precise viewport/device sizing.
See the world's web. Country-specific proxies set IP, language, time zone, and geolocation.
One call, image back. No browser cluster to run, no SDK required.

Three ways to connect

Method	For	How
MCP server	Claude Desktop, Cursor, Cline, LangChain, CrewAI	`npx -y site-shot-mcp`
GPT Actions / OpenAPI	Custom GPTs, OpenAPI clients	`/openapi.json`
Plain HTTP API	Any language / framework	See the API schema (example below)

Works with: Claude · Cursor · Cline · LangChain · CrewAI · OpenAI GPTs · n8n · any MCP client.

Guides: Best screenshot MCP servers in 2026 · Screenshots for AI agents over MCP · 8-tool screenshot API comparison.

Discovery entry points

Use these URLs to discover and integrate Site-Shot from AI agents and agent runtimes.

/llms.txt — concise Markdown discovery file.
/llms-full.txt — combined Markdown context for longer agent reads.
/openapi.json — GPT Actions-ready OpenAPI schema.
/api/v1/agent/plans/ — public plan discovery endpoint.
/api/v1/agent/docs/*.md — focused Markdown pages for pricing, signup, auth, billing, usage, screenshot API, security, and API key handling.
/.well-known/ai-plugin.json — legacy ChatGPT plugin-compatible manifest pointing to OpenAPI.
/.well-known/agent-card.json — agent card describing Site-Shot capabilities.
/.well-known/agent.json — compatibility alias for agent runtimes that look for this well-known agent manifest path.

Recommended agent flow

Read /llms.txt and the relevant Markdown docs.
Import /openapi.json into GPT Actions or another OpenAPI-compatible agent runtime.
List public plans, start email-gated signup, and let the user confirm setup on Site-Shot.
Authorize with OAuth scopes, create a Stripe Checkout session, and let the user confirm payment in Stripe.
Read usage/subscription status and reveal the screenshot API key only through the explicit API-key action.

Security boundaries

Agents do not collect card details. Payments are confirmed by the user in Stripe Checkout. The full screenshot API key is never returned in generic profile or status calls; it requires the explicit api_key:read scoped action.

Quick start

Once a screenshot API key is revealed, capture a full-page screenshot with a single request.

curl -X POST https://api.site-shot.com/v1/screenshot \
  -H "Authorization: Bearer $SITESHOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "width": 1280, "full_page": true}' \
  --output screenshot.png

FAQ

Is there a screenshot MCP server?

Yes — Site-Shot ships an open-source MCP server (site-shot-mcp) that gives Claude and other AI agents two tools to capture website screenshots, with real Chromium rendering and automatic ad/cookie-banner removal.

How do I give Claude the ability to take screenshots?

Add the Site-Shot MCP server to your Claude Desktop config (snippet above) with your API key. Claude can then capture any URL and view the image inline.

Why use a screenshot API instead of Puppeteer for my agent?

You skip running and scaling a headless-browser cluster, and you get proxies, ad/cookie removal, and full-page capture out of the box — a single call returns the image.

Does it reduce token usage for vision models?

Yes — removing ads and cookie banners produces a cleaner image with less to process, which lowers the token cost of feeding screenshots to a vision model.