← All integrations
Import.io + Claude Code

Web scraping in Claude Code with the Import.io plugin

Two commands install the Import.io Web Scraper plugin: the hosted Import.io Web Scraper MCP server, plus a skill that tells Claude Code to use it for scraping, browser automation and extraction.

Connects via
MCP
Setup
1 min
Available on
10,000 free successful calls, then $0.0002 per call
Get an MCP keyRead the MCP docs
claude plugin marketplace add import-io/mcp-plugin
claude plugin install import-io-web-scraper@import-io-plugins

How it connects.

Source

The web

Any public page, rendered, through managed proxies

Engine

Import.io

Rendering, proxy routing, captcha handling, extraction

Path

Import.io MCP

https://mcp.import.io/mcp

Destination

Claude Code

One plugin install: Claude Code scrapes, tests and builds against live pages.

What teams do with it.

Build a scraper against the real page

Claude Code fetches the rendered page, inspects the HTML, writes the parser in your repo and checks it against live output.

Fetch this product page, find the price selector and write a parser with a test.

Generate fixtures from production pages

Capture rendered HTML and screenshots of the pages your code handles and commit them as test fixtures.

Save rendered HTML for these 20 URLs into tests/fixtures.

Run data jobs from the terminal

Collect a dataset across every page of a listing, clean it in code and write CSV or JSON to disk in one session.

Scrape every listing on this search page across all pages and write listings.csv.

Set it up.

  1. Create an MCP key at mcp.import.io/app/keys/new.
  2. Add the Import.io marketplace: claude plugin marketplace add import-io/mcp-plugin.
  3. Install the plugin: claude plugin install import-io-web-scraper@import-io-plugins.
  4. Paste your mcp_live_ key when Claude Code prompts for it, then run /mcp to see import-io-web-scraper.

Questions.

What does the plugin add beyond the MCP server?

An agent skill. It tells Claude Code to reach for the Import.io tools by default for scraping, browser automation, screenshots, HTML capture and structured extraction.

Where is the plugin source?

github.com/import-io/mcp-plugin, MIT licensed. The plugin connects to the hosted server at https://mcp.import.io/mcp, so there is nothing to run locally.

What does the Import.io MCP cost?

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.

OAuth or API key?

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.

Which tools does the server expose?

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.

Related integrations.

All 50 integrations

MCP

Claude

Live, structured web data as tools in Claude on the web and Claude Desktop.

Setup 2 minMCP

Cursor

Cursor’s agent reads live pages while it writes your scraper, tests and data code.

Setup 2 minMCP

VS Code

GitHub Copilot agent mode with live web data from Import.io.

Setup 3 minMCP

MCP SDKs

Call Import.io tools directly from the official Python and TypeScript SDKs.

Setup 10 min

Give Claude Code
the live web.

Get an MCP keyRead the MCP docs