Integration

ScrapeNinja integration

ScrapeNinja fetches any web page through rotating proxies and returns its HTML, final URL, status and headers as JSON. Use scrape for a fast request with a Chrome TLS fingerprint (no JavaScript), scrape_js to render the page in a real Chrome browser (wait for a CSS selector, block images, take a screenshot, capture an AJAX response), or scrape_js_v2 for the newer browser engine aimed at sites protected by Cloudflare, Datadome or Kasada. An optional JavaScript extractor function (Cheerio) turns the HTML into clean JSON on ScrapeNinja's side. Authentication is an APIRoad API key sent in the X-Apiroad-Key header (keys bought on RapidAPI use another host and header and do not work here).

Connect ScrapeNinja How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with ScrapeNinja

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.

scrapeScrapePOSTFetches a URL with a Chrome TLS fingerprint and no JavaScript (fastest engine); returns body (HTML), info.statusCode, info.finalUrl, headers, and extractor output if sent. Use scrape_js when the page needs JavaScript.
scrape_jsScrape jsPOSTRenders a URL in a real Chrome browser (JavaScript, waitForSelector, screenshot, AJAX capture); returns body (rendered HTML), info incl. screenshot URL, and extractor output if sent. Slower than scrape.
scrape_js_v2Scrape js v2POSTRenders a URL with ScrapeNinja's newer real-browser engine, which has a better success rate on sites protected by Cloudflare, Datadome, Kasada or PerimeterX. Same inputs as scrape_js minus iframe, AJAX capture and viewport options.

Use ScrapeNinja from Claude Code, Cursor or Codex

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

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