← All integrations
Import.io + Gemini CLI

Web scraping MCP for Gemini CLI

Add Import.io Web Scraper MCP to settings.json and Gemini CLI can fetch rendered pages, target a country and return structured data from the terminal.

Connects via
MCP
Setup
2 min
Available on
10,000 free successful calls, then $0.0002 per call
Get an MCP keyRead the MCP docs
settings.json
{
  "mcpServers": {
    "importio": {
      "httpUrl": "https://mcp.import.io/mcp",
      "headers": {
        "Authorization": "Bearer mcp_live_..."
      }
    }
  }
}

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

Gemini CLI

Live page data and extraction tools in Google’s terminal agent.

What teams do with it.

Terminal research with sources

Ask a question and Gemini reads the pages that answer it, live.

Find the current list price of these five SKUs on the manufacturer’s site.

Scripts from real output

Generate a script from the actual response shape of a page, not a guess.

Fetch this page and write a Python script that extracts the table into CSV.

Quick checks across markets

Compare what a page shows in different countries in one command.

Load this product page from the US, the UK and Japan and compare prices.

Set it up.

  1. Open ~/.gemini/settings.json, or .gemini/settings.json in your project.
  2. Add importio under mcpServers with httpUrl and your bearer key.
  3. Run /mcp in Gemini CLI to confirm the tools loaded.

Questions.

Project or user settings?

Either. Project settings in .gemini/settings.json override user settings in ~/.gemini/settings.json.

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 Code

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

Setup 1 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

Google ADK

Import.io as an MCPToolset for Agent Development Kit agents.

Setup 10 min

Give Gemini CLI
the live web.

Get an MCP keyRead the MCP docs