Parsers written against real pages
Cascade reads the rendered page before it writes a line of parsing code.
Fetch this listing page and write a parser for title, price and seller.
Add Import.io Web Scraper MCP to mcp_config.json and Cascade can open real pages, choose a proxy country and extract fields while it codes.
{
"mcpServers": {
"importio": {
"serverUrl": "https://mcp.import.io/mcp",
"headers": {
"Authorization": "Bearer mcp_live_..."
}
}
}
}Any public page, rendered, through managed proxies
Rendering, proxy routing, captcha handling, extraction
https://mcp.import.io/mcp
Cascade gets live web data tools for scraping, testing and research.
Cascade reads the rendered page before it writes a line of parsing code.
Fetch this listing page and write a parser for title, price and seller.
Check competitor docs, changelogs and pricing pages while you build.
Summarize the pricing tiers on these three competitor pages.
Screenshots and rendered HTML from the markets your users are in.
Screenshot our checkout page from the UK and from the US.
~/.codeium/windsurf/mcp_config.json.https://mcp.import.io/mcp and your bearer key.Sign in at mcp.import.io and create a key. It starts with mcp_live_. Use a separate key per machine so you can revoke one without touching the others.
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.
Cursor’s agent reads live pages while it writes your scraper, tests and data code.
Setup 2 minMCPGitHub Copilot agent mode with live web data from Import.io.
Setup 3 minMCPHosted web scraping tools for Cline’s autonomous coding agent.
Setup 2 minMCPOne plugin install: Claude Code scrapes, tests and builds against live pages.
Setup 1 min