Agent mode that can see the page
Copilot updates selectors and parsers against the page as it renders today.
Fetch the rendered HTML of this URL and update the scraper’s selectors.
Add Import.io Web Scraper MCP to .vscode/mcp.json and Copilot’s agent mode gets tools to fetch, render and extract from real pages.
{
"inputs": [
{ "type": "promptString", "id": "importio-key",
"description": "Import.io MCP key", "password": true }
],
"servers": {
"importio": {
"type": "http",
"url": "https://mcp.import.io/mcp",
"headers": { "Authorization": "Bearer ${input:importio-key}" }
}
}
}Any public page, rendered, through managed proxies
Rendering, proxy routing, captcha handling, extraction
https://mcp.import.io/mcp
GitHub Copilot agent mode with live web data from Import.io.
Copilot updates selectors and parsers against the page as it renders today.
Fetch the rendered HTML of this URL and update the scraper’s selectors.
Commit mcp.json with a password prompt for the key. Each developer brings their own.
Collect the top 20 search results for “standing desk” on this retailer.
Extract a table into your workspace and open it in a Jupyter notebook in the same window.
Extract this table into data/raw.csv.
.vscode/mcp.json in your workspace, or run MCP: Add Server from the command palette.No. VS Code connects to the hosted endpoint over HTTPS. Nothing to install beyond the config 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.
Cursor’s agent reads live pages while it writes your scraper, tests and data code.
Setup 2 minMCPCascade gets live web data tools for scraping, testing and research.
Setup 2 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