Integration

Site-Shot integration

Site-Shot captures public web pages in a real Chromium browser. An agent can take a screenshot of a URL as a PNG, JPEG or WebP file (viewport or full page, custom size and zoom, ads and cookie banners blocked, injected JavaScript, custom request headers, rendered from a chosen country, language, time zone and GPS position), or get the rendered page as Markdown (optionally with its HTML source). Each capture counts as one screenshot against the plan's quota (100 a month on the free plan; country targeting needs a paid plan). Scheduled captures, the onboarding and billing Agent API and API key handling are not exposed. Authentication is the screenshot API key from the Site-Shot dashboard, sent as the userkey query parameter.

Connect Site-Shot How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Site-Shot.Built from the 2 Site-Shot tools below, on the connection you add once.

What you can do with Site-Shot

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.

Page, 1 operation

get_page_markdownGet page markdownGETAgents: ask firstRenders a public web page in a real browser and returns its rendered view as Markdown (up to 40,000 characters). Check markdown_status and error before reading markdown. Counts as one screenshot against the plan's quota.

Screenshot, 1 operation

capture_screenshotCapture screenshotGETAgents: ask firstCaptures a public web page in a real browser and returns the image as a stored file (PNG by default, or JPEG or WebP). Each call counts as one screenshot against the plan's quota. For the page's text as Markdown use get_page_markdown.

Use Site-Shot from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Site-Shot once
Add your Site-Shot 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.