Integration

GetScreenshot integration

GetScreenshot, by Rasterwise, captures websites with headless Chrome: give it a URL and get back a link to a PNG or JPEG screenshot, or an A4 PDF of the page. Control the viewport or a device preset, capture the full page or one element, hide cookie banners and chat widgets, inject CSS or JavaScript, click before capturing, highlight text, and optionally ask an AI question about the capture. Each call renders a fresh capture (no caching), usually in 8 to 22 seconds with a 30-second timeout, and images are kept for 30 days. Not exposed: the account usage route (its response is not documented) and the bypass-login option, which sends a third-party password in the URL. Authentication is an API key from the Rasterwise dashboard, sent as the apikey query parameter.

Connect GetScreenshot How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in GetScreenshot.Built from the 1 GetScreenshot tool below, on the connection you add once.

What you can do with GetScreenshot

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.

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

capture_screenshotCapture screenshotGETCaptures a web page and returns screenshotImage (image URL, kept 30 days), or pdfFile when pdf=true. Waits for the capture, usually 8 to 22 s, 30 s timeout. email and webhook trigger a delivery: leave them out unless asked.

Use GetScreenshot from Claude Code, Cursor or Codex

Connect GetScreenshot in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its GetScreenshot 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 GetScreenshot

Create your workspace
Sign up free. Nothing to install.
Connect GetScreenshot once
Add your GetScreenshot 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.