# scrapeunblocker-mcp-remote

A remote MCP server that connects to ScrapeUnblocker, pulling page HTML, parsed data, Google results and ready-made site plugins into your agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: ScrapeUnblocker
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ScrapeUnblocker/scrapeunblocker-mcp-remote
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/scrapeunblocker-mcp-remote

## What it does

The server runs as an HTTP endpoint at `https://mcp.scrapeunblocker.com/mcp` and exposes tools for working with pages: `fetch_html` returns rendered HTML, `fetch_markdown` strips scripts and navigation down to clean readable text, and `fetch_parsed` returns AI-structured JSON. There's a `google_search` tool plus a combined `search_and_read` that runs a search and reads the top pages in one call.

For pages that need interaction, `browse_page` takes an ordered list of steps - clicking, typing, scrolling, waiting - and runs them in a real browser before capturing the result; `list_elements` finds the selectors for those steps. Over a hundred site plugins, covering Amazon, Walmart, Zillow, Indeed, YouTube and others, are reachable through `run_plugin` or as standalone tools like `amazon_search` and `youtube_transcript`.

Running any tool requires a ScrapeUnblocker account tied to an API key or OAuth login; listing the available tools works without credentials, but calling them doesn't.

## Requirements
- Remote server: `https://mcp.scrapeunblocker.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http scrapeunblocker-mcp-remote https://mcp.scrapeunblocker.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add scrapeunblocker-mcp-remote --url https://mcp.scrapeunblocker.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapeunblocker-mcp-remote": {
            "url": "https://mcp.scrapeunblocker.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapeunblocker-mcp-remote": {
            "type": "http",
            "url": "https://mcp.scrapeunblocker.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http scrapeunblocker-mcp-remote https://mcp.scrapeunblocker.com/mcp
```

## When to use it
- pull a page's HTML or Markdown version
- turn a page into structured JSON via AI parsing
- run a Google search and read top results in one step
- click, type and scroll through a page via scripted steps
- pull data from Amazon, Zillow, Indeed and other sites through built-in plugins

## Example prompts
- Fetch the Markdown version of this page with fetch_markdown
- Search Google for this term and read the top five results
- Pull the review list for this Amazon product with amazon_reviews

## Similar
- [remote-browser](https://affpapa.org/en/nevibecode/skills/remote-browser.md) — skill · 4700 installs
- [browser-automation](https://affpapa.org/en/nevibecode/skills/browser-automation.md) — skill · 636 installs
- [Actionbook](https://affpapa.org/en/nevibecode/mcp/actionbook.md) — MCP server · ★ 1620
- [google-search-browser-use](https://affpapa.org/en/nevibecode/skills/google-search-browser-use.md) — skill · 1900 installs
- [scraping-google-search-results](https://affpapa.org/en/nevibecode/skills/scraping-google-search-results.md) — skill · 759 installs
- [scrapeless-mcp-server](https://affpapa.org/en/nevibecode/mcp/scrapeless-mcp-server.md) — MCP server · ★ 170

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md