Integration

CustomJS integration

CustomJS is an API toolkit for automations that renders documents and drives a real browser. Convert HTML, or an HTML template filled with JSON data, into a PDF file; capture a PNG screenshot of any web page after clicking, typing, waiting or scrolling, optionally cropped; and scrape a website either by describing the goal to an AI browsing agent or by scripting exact browser steps, getting back extracted data, text, HTML, markdown or screenshot URLs. Left out: the Markdown to PDF route (no request reference), running JavaScript inline or as stored functions (which also back the PDF to PNG, PDF to text, merge, extract pages and compress tools), and the HTML Pages hosting API on its separate host. Authentication is the API key from the CustomJS dashboard, sent in the x-api-key header.

Connect CustomJS How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with CustomJS

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.

Ai scraper, 1 operation

scrape_websiteScrape websitePOSTScrapes a website in a real browser: give a goal and an AI agent browses and returns data, text, HTML, markdown or a screenshot URL, or give a url and exact steps and get the extractions. Clicks and typing act on the live site.

Html2pdf, 1 operation

html_to_pdfHtml to pdfPOSTRenders HTML in a real Chromium instance and returns the PDF as a file. Give data to fill the HTML as a Nunjucks template ({{ variable }} placeholders). The page is A4 unless a width and height in millimeters are given.

Screenshot, 1 operation

take_screenshotTake screenshotPOSTLoads a URL in a real Chromium instance, optionally runs commands first (click, type, wait, scroll; they act on the live site), and returns a PNG screenshot of the page, or of a cropped area, as a file.

Use CustomJS from Claude Code, Cursor or Codex

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

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