Selectors from the live DOM
The agent reads the page as rendered, not as guessed, and writes selectors that match.
Open this page and write a Playwright test that asserts the price element.
One entry in mcp.json and Cursor’s agent connected to Import.io Web Scraper MCP can fetch rendered pages, inspect HTML and extract data while it works on your code.
{
"mcpServers": {
"importio": {
"url": "https://mcp.import.io/mcp"
}
}
}{
"mcpServers": {
"importio": {
"url": "https://mcp.import.io/mcp",
"headers": {
"Authorization": "Bearer ${env:IMPORTIO_MCP_KEY}"
}
}
}
}Any public page, rendered, through managed proxies
Rendering, proxy routing, captcha handling, extraction
https://mcp.import.io/mcp
Cursor’s agent reads live pages while it writes your scraper, tests and data code.
The agent reads the page as rendered, not as guessed, and writes selectors that match.
Open this page and write a Playwright test that asserts the price element.
Pull a realistic sample of products, listings or reviews into a JSON file for your app.
Grab 50 real product records from this category into seed/products.json.
Fetch your own pages from another country to confirm geo pricing, currency and redirects.
Load our pricing page from Germany and confirm it shows EUR.
~/.cursor/mcp.json.https://mcp.import.io/mcp.mcp_live_ key.Both work. Put it in .cursor/mcp.json to share with the repo, or ~/.cursor/mcp.json to use it everywhere. Reference the key from an environment variable rather than writing it into the file.
Signup includes 10,000 successful calls. After that it is $0.0002 per successful call. Setup requests, tool listings, malformed requests, blocked requests and failed upstream calls are never billed, and you can set a monthly spend limit that stops paid usage when reached.
Use OAuth in interactive clients that support it: the client opens a sign-in, stores the credentials and reuses them. Use an API key for scripts, servers and clients without OAuth, sent as Authorization: Bearer mcp_live_…. Keep keys out of prompts and shared config files.
importio_web_fetch, importio_render, importio_extract_data and importio_get_html, page helpers such as importio_page_text, importio_page_links and importio_search_cards, and browser actions for clicks, form input, scrolling, pagination, waits, screenshots and captcha handling. Requests can pick a proxy country and type, with bounded retries when a page blocks.
Cascade gets live web data tools for scraping, testing and research.
Setup 2 minMCPGitHub Copilot agent mode with live web data from Import.io.
Setup 3 minMCPOne plugin install: Claude Code scrapes, tests and builds against live pages.
Setup 1 minMCPHosted web scraping tools for Cline’s autonomous coding agent.
Setup 2 min