ScrapeUnblocker Documentation

The official MCP server lets Claude (Desktop, Code, and the web app), ChatGPT, and any other Model Context Protocol client fetch any web page’s HTML - or AI-parsed JSON, or Google results - through ScrapeUnblocker, bypassing anti-bot protection (Cloudflare, DataDome, PerimeterX, Akamai, Shape). You bring your own API key. Nothing is proxied through a shared account.

npx -y scrapeunblocker-mcp

Requires Node.js 18+. Published on npm as scrapeunblocker-mcp.

Using Claude Code? The Claude Code plugin installs this same server with two commands, prompts for your API key and keeps it in your OS keychain, and adds a /scrape-url command plus reference skills.

Tools

Tool	What it does
`fetch_html`	Fetch the fully rendered HTML of any URL.
`fetch_parsed`	Fetch a page and return AI-parsed structured JSON.
`google_search`	Run a Google search and return organic results as JSON.
`fetch_markdown`	Fetch a page and return it as clean Markdown: the main content with absolute links, without scripts, styles, navigation or footer. Usually 2-25% the size of the HTML, so it is the cheap way for the assistant to read a page. Billed as one request.
`search_and_read`	Search Google and read the top results in one call: Google’s AI Overview (when there is one), the first 1-5 result pages as Markdown, and the other results as title, URL and snippet. Billed as one search plus one request per page read.
`list_elements`	List a page’s interactive elements (buttons, inputs, links, forms) with ready-to-use selectors.
`browse_page`	Run browser steps on a page (click, type, select, press a key, scroll, wait) after it loads, then return the resulting HTML. Find the selectors with `list_elements` first. The one tool not marked read-only, because the steps act on the website. Billed as one request.
`list_plugins`	List the ready-made site plugins (Amazon, Walmart, Zillow, Booking.com, Indeed, Google Trends, YouTube, App Store, Ahrefs and 100+ more) with their parameters. Free - it calls nothing.
`run_plugin`	Run one site plugin and return its structured JSON. Each run is billed like an API request.
`amazon_search`, `amazon_product`, `amazon_reviews`, `walmart_search`, `ebay_search`, `google_shopping`, `google_local`, `maps_place_details`, `google_images`, `youtube_search`, `youtube_transcript`, `zillow_search`, `indeed_jobs`, `trustpilot_reviews`, `booking_hotels`	The most-used site plugins as tools of their own, with their parameters in the tool schema, so the assistant calls them in one step. Same JSON as `run_plugin`, billed the same way.

Get an API key

Grab your key from the dashboard. The server reads it from the SCRAPEUNBLOCKER_KEY environment variable, so each user runs it with their own key.

Install

Claude Code
Claude Desktop
Cursor
VS Code
Any MCP client

claude mcp add scrapeunblocker \
  --env SCRAPEUNBLOCKER_KEY=YOUR_API_KEY \
  -- npx -y scrapeunblocker-mcp

Add this to your claude_desktop_config.json (Settings → Developer → Edit Config), then restart Claude Desktop:

{
  "mcpServers": {
    "scrapeunblocker": {
      "command": "npx",
      "args": ["-y", "scrapeunblocker-mcp"],
      "env": {
        "SCRAPEUNBLOCKER_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Add to Cursor installs the hosted server. Then open Cursor Settings → MCP, edit scrapeunblocker and replace YOUR_API_KEY with your key.Or add it to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project) yourself:

{
  "mcpServers": {
    "scrapeunblocker": {
      "url": "https://mcp.scrapeunblocker.com/mcp",
      "headers": {
        "x-scrapeunblocker-key": "YOUR_API_KEY"
      }
    }
  }
}

Add the server from a terminal. VS Code asks for your key the first time the server starts and keeps it in its secret storage:

code --add-mcp '{"name":"scrapeunblocker","type":"stdio","command":"npx","args":["-y","scrapeunblocker-mcp"],"env":{"SCRAPEUNBLOCKER_KEY":"${input:scrapeunblocker-key}"}}'

Or put this in .vscode/mcp.json:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "scrapeunblocker-key",
      "description": "ScrapeUnblocker API key",
      "password": true
    }
  ],
  "servers": {
    "scrapeunblocker": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "scrapeunblocker-mcp"],
      "env": {
        "SCRAPEUNBLOCKER_KEY": "${input:scrapeunblocker-key}"
      }
    }
  }
}

The server speaks MCP over stdio. Start it with your key in the environment:

SCRAPEUNBLOCKER_KEY=YOUR_API_KEY npx -y scrapeunblocker-mcp

Once connected, the tools appear automatically and the assistant calls them when it needs to read a page, search the web or reach a page that would otherwise be blocked.

Hosted connector (claude.ai web & mobile)

Don’t want to run anything locally? Use the hosted server. It works across claude.ai (web and mobile), Claude Desktop, and Claude Code - no install. There are two ways to connect: sign in with OAuth (no key to copy) or use your API key. On claude.ai both start the same way: Customize → Connectors → Add → Add custom connector, name ScrapeUnblocker, URL https://mcp.scrapeunblocker.com/mcp.

claude.ai pre-selects No sign-in under Authentication for this server, because it can list the tools without credentials. Keep it only for the API-key setup. For OAuth, switch it to Sign in now - otherwise the connector is added and shows its tools, but every call fails with missing token.

Connect with your ScrapeUnblocker login - no key to paste, and it bills your own account.

On claude.ai: Customize → Connectors → Add → Add custom connector.
URL: https://mcp.scrapeunblocker.com/mcp (no ?key=).
Authentication: choose Sign in now.
Open Advanced and set OAuth Client ID to:
5BM5Wk2dE4ABkDITmuKfemPLnn3QQ8jd
Leave OAuth Client Secret empty.
Add, then sign in with your ScrapeUnblocker account and Authorize.

The tools then appear everywhere you use Claude. You need a ScrapeUnblocker account for the email you sign in with - create a free one first if you don’t have it.

Or use your API key

claude.ai:

Customize → Connectors → Add → Add custom connector.
URL: https://mcp.scrapeunblocker.com/mcp.
Authentication: leave No sign-in.
Under Request headers click Add header, pick Authorization from the dropdown and enter the value:
Bearer YOUR_API_KEY
Type the word Bearer, a space, then your key - claude.ai does not add Bearer for you.
Add.

Don’t use Custom header with x-scrapeunblocker-key. claude.ai only accepts approved header names and rejects the connector with “The header name … isn’t approved”. Use Authorization as above.

claude.ai warns that without sign-in anyone with the server URL can use the connector. That is fine here: the tools only run with a valid API key, and the key you enter in the header is stored by claude.ai and never shown again. If you prefer, you can skip the header and put the key in the URL instead: https://mcp.scrapeunblocker.com/mcp?key=YOUR_API_KEY (the key is then visible to anyone who opens the connector’s settings). Claude Code:

claude mcp add --transport http scrapeunblocker \
  "https://mcp.scrapeunblocker.com/mcp?key=YOUR_API_KEY"

The key can also be sent as an Authorization: Bearer YOUR_API_KEY header instead of the query parameter.

ChatGPT

ChatGPT connects to the same hosted server as a custom connector, with your API key in the URL. Set it up in ChatGPT on the web (chatgpt.com - not the desktop app) under Settings → Plugins → Developer mode. See the full, screenshot-by-screenshot ChatGPT setup guide.

Example prompts

“This page keeps blocking me: https://example-shop.com/product/123. Use fetch_html to get it and list the price.”
“Fetch the parsed data for https://www.amazon.com/dp/B08N5WRWNW and summarise the product.”
“Search Google for best running shoes 2026 and give me the top 5 links, then fetch the first one.”
“Read https://en.wikipedia.org/wiki/Web_scraping as Markdown and summarise it in five bullets.” (uses fetch_markdown)
“Search the web for the current population of Vilnius and cite the pages you read.” (uses search_and_read)
“Find coffee makers on Target under $50 and compare them with Walmart’s.” (uses run_plugin)
“Show Google Trends for coffee vs tea in the US over the last year.”

Configuration

Environment variable	Required	Description
`SCRAPEUNBLOCKER_KEY`	Yes	Your API key. `SCRAPEUNBLOCKER_API_KEY` is also accepted.
`SCRAPEUNBLOCKER_BASE_URL`	No	Override the API base URL (defaults to `https://api.scrapeunblocker.com`).

The MCP server is a thin wrapper over the Node.js SDK and the same getPageSource endpoint. Anything the tools return is exactly what the API returns - see the guides for response shapes.

Source

npm: scrapeunblocker-mcp
GitHub: ScrapeUnblocker/scrapeunblocker-mcp

Get Started

No-code area

Spider Cloud

Plugins

AI Assistants

Guides

Code Examples

MCP Server

Tools

Get an API key

Install

Hosted connector (claude.ai web & mobile)

Or use your API key

ChatGPT

Example prompts

Configuration

Source

​Tools

​Get an API key

​Install

​Hosted connector (claude.ai web & mobile)

​Sign in with OAuth (recommended on claude.ai)

​Or use your API key

​ChatGPT

​Example prompts

​Configuration

​Source

Tools

Get an API key

Install

Hosted connector (claude.ai web & mobile)

Sign in with OAuth (recommended on claude.ai)

Or use your API key

ChatGPT

Example prompts

Configuration

Source