Integration

Snapshot Site integration

Snapshot Site renders web pages in a real browser. Capture a page as a PNG, JPEG, WebP or PDF file or as its rendered HTML (viewport or full page, after a delay, with cookie banners hidden, elements removed by CSS selector and custom JavaScript run first), analyze a page with AI (a summary, its topics and a quality check for blank pages, CAPTCHAs, HTTP status and readability), and compare two page states or two PNG images into a diff image with mismatch metrics. Every call counts against the plan's monthly requests (free plan: 50 requests a month; paid plans from 7 euros a month, with overage fees past a soft limit). Authentication is an API key created in the Snapshot Site Console, sent in the x-snapshotsiteapi-key header.

Connect Snapshot Site How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with Snapshot Site

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_advanced_screenshotCapture advanced screenshotPOSTAgents: ask firstCaptures a web page like capture_screenshot, but can first remove elements by CSS selector (hide) and run custom JavaScript in the page (javascriptCode). Returns a link to the stored file, or the rendered HTML. Billed as one plan request.
capture_screenshotCapture screenshotPOSTAgents: ask firstCaptures a web page in a real browser and returns a link to the stored PNG, JPEG, WebP or PDF file, or the rendered HTML. Options: viewport size, full page, delay, hidden cookie banners. Billed as one plan request.

Page analysis, 1 operation

analyze_pageAnalyze pagePOSTAgents: ask firstCaptures a web page and adds AI analysis on request: a summary and topics (enableSummary) and a quality check (enableQuality: blank page, CAPTCHA, HTTP status, readability). Returns the capture link with the analysis. Billed as one plan request.

Visual diff, 1 operation

compare_pagesCompare pagesPOSTAgents: ask firstCompares two page states (two live URLs, two PNG image URLs, or one of each) and returns links to the before, after and diff images plus mismatch metrics (pixels and percent that differ). Billed as one plan request.

Use Snapshot Site from Claude Code, Cursor or Codex

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

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