Integration

ScreenshotOne integration

ScreenshotOne renders web pages with a hosted Chrome browser. An agent can take a screenshot or PDF of a URL, or render HTML or Markdown, with control over viewport or emulated device, full-page capture, an element selector or clip area, dark mode, injected CSS and JavaScript, clicks, waits, and blocking of cookie banners, ads, chats and trackers; record an animated screenshot (MP4, MOV, AVI, WebM or GIF, optionally scrolling); read the plan's usage; and list the devices it can emulate. Each rendered screenshot, PDF or video costs one credit of the monthly allowance (cached and failed requests do not). Not exposed: bulk requests, async webhooks, uploads to your own S3 storage, the OpenAI vision add-on, request signing and the HTML/Markdown text output formats. Authentication is the access key sent as the access_key query parameter.

Connect ScreenshotOne How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ScreenshotOne.Built from the 4 ScreenshotOne tools below, on the connection you add once.

What you can do with ScreenshotOne

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.

Animated screenshot, 1 operation

take_animated_screenshotTake animated screenshotGETRecords a URL, HTML or Markdown page as a video or animated GIF (output file), still or scrolling (scenario scroll), up to 30 seconds. Costs one credit per render.

Device, 1 operation

list_devicesList devicesGETLists the devices ScreenshotOne can emulate; pass a device id as viewport_device to take_screenshot or take_animated_screenshot.

Screenshot, 1 operation

take_screenshotTake screenshotGETRenders a URL, HTML or Markdown and returns the screenshot or PDF as a file (output file). Costs one credit per render; cache hits and failed requests are free.

Usage, 1 operation

get_usageGet usageGETReturns the plan's credit usage for the current period (total, available, used) and the per-minute request bucket (concurrency limit, remaining, reset).

Use ScreenshotOne from Claude Code, Cursor or Codex

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

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