Integration

Screenshotty integration

Screenshotty captures a web page, or a raw HTML document, in a real browser and returns it as an image (PNG, JPEG, WebP, GIF, JPEG 2000 or TIFF) or a PDF, either as a stored file or as a hosted image URL with the page's HTML. Options cover viewport size and device presets, full page or a single CSS selector, cropping, wait conditions, injected JavaScript and CSS, cookies and request headers, ad and cookie-banner blocking, dark mode, browser language and geo-targeting by country. Every capture counts against the plan's monthly screenshot quota, and rate limits depend on the plan. The RapidAPI listing of the same API is not used. Authentication is an API key created in the Screenshotty dashboard (Dashboard, API Keys), sent in the x-api-key header.

Connect Screenshotty How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Screenshotty.Built from the 3 Screenshotty tools below, on the connection you add once.

What you can do with Screenshotty

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Screenshot, 2 operations

capture_screenshotCapture screenshotPOSTAgents: ask firstCaptures a web page (url) or an HTML document (html) in a real browser and returns the image or PDF as a stored file. Pass exactly one of url or html. Each call counts against the plan's monthly screenshot quota.
capture_screenshot_urlCapture screenshot urlGETAgents: ask firstCaptures a web page (url) or a short HTML document (html) and returns a hosted URL of the image or PDF, its width, height and MIME type, and the page's rendered HTML. Pass exactly one of url or html. Counts against the monthly screenshot quota.

Country, 1 operation

list_countriesList countriesGETAgents: ask firstLists the two-letter country codes the country parameter of capture_screenshot and capture_screenshot_url accepts (locations the page can be loaded from through a proxy).

Use Screenshotty from Claude Code, Cursor or Codex

Connect Screenshotty in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Screenshotty operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Screenshotty

Create your workspace
Sign up free. Nothing to install.
Connect Screenshotty once
Add your Screenshotty connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.