Integration

Zyte integration

Enterprise web scraping and data extraction platform. The Zyte API provides a single endpoint for browser rendering, HTTP requests, screenshots, and AI-powered structured data extraction (products, articles, job postings). Scrapy Cloud provides spider job management and data storage. Reliable and scalable web data solutions with built-in anti-bot bypass.

Connect Zyte How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Zyte.Built from the 7 Zyte tools below, on the connection you add once.

Common Zyte use cases

Run a web spider
Debug spider errors
Stop a runaway spider
Clean up old crawl jobs
Monitor running spider jobs
Download scraped product data
Extract product data from e-commerce pages
Remove test jobs
Schedule a crawl job
Monitor crawl progress

What you can do with Zyte

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.

Spider job, 4 operations

scrapy_delete_jobsScrapy delete jobsPOSTDeletes one or more Scrapy Cloud spider jobs.
scrapy_list_jobsScrapy list jobsGETLists Scrapy Cloud spider jobs with optional filters.
scrapy_run_jobScrapy run jobPOSTSchedules a Scrapy Cloud spider job for execution.
scrapy_stop_jobScrapy stop jobPOSTStops a running Scrapy Cloud spider job.

Data, 1 operation

extractExtractPOSTExtracts data from a web page via the single Zyte API endpoint. Supports browser rendering, raw HTTP, screenshots, and AI-powered structured extraction for products, articles, job postings, and more.

Items, 1 operation

scrapy_get_itemsScrapy get itemsGETRetrieves scraped items from a Scrapy Cloud spider job.

Logs, 1 operation

scrapy_get_logsScrapy get logsGETRetrieves log entries from a Scrapy Cloud spider job.

Use Zyte from Claude Code, Cursor or Codex

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

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

Zyte integration FAQ

What can you do with the Zyte integration?

LiveContext exposes 7 operations on Zyte, covering spider job, data, items and logs. Common uses include Run a web spider, Debug spider errors and Stop a runaway spider.