# Scrappy Cloud Browser

> Scrappy Cloud Browser is a paid MCP server for browser automation. Hosted cloud browsers for agents with saved logins, residential IPs and live takeover. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://scrappy.gg/integrations/mcp
- **MCP Registry name:** gg.scrappy/cloud-browser
- **Categories:** browser automation, web search and scraping
- **Listing updated:** 2026-11-15

## About

Scrappy's endpoint gives an agent a real headful Chrome running in the cloud rather than on your own machine. Sessions exit through a residential connection, with the timezone matched to the exit IP, and saved logins are pinned to the IP they were made on so a session signed in last week still works. A live viewer lets a person step in and click or type when a site needs a human.

The server is stateless: a session id is the only handle, so many agents can share one key from any machine. Tools cover sessions, reading pages as an accessibility tree, acting (click, type, drag, up to 25 actions in one batch), waiting, dialogs, CAPTCHA detection, tabs, uploads, downloads, cookies and recordings. The registry lists 57 browser tools, while the site counts 62 including the rest of the platform.

Keys use browser:read and browser:write scopes and can be capped on concurrent sessions and monthly minutes. Authentication is a Scrappy API key in the Authorization header.

## Features

- **Cloud Chrome sessions:** Headful Chrome on a residential exit, driven through MCP or the REST API.
- **Saved logins:** Start a session already signed in, from the IP the login was made on.
- **Live human takeover:** Open a viewer to click and type yourself from a laptop or phone.
- **Batch actions:** Run up to 25 browser actions in one call.
- **Scoped keys:** Limit a key by scope, concurrent sessions and monthly minutes.
- **Stateless server:** No process to keep alive; scale agents from any machine.
- **Recordings and captures:** Screenshots, console, network and session recordings.

## Good for

- Let an agent work in a site that requires a login
- Run scraping jobs from a residential IP
- Hand a stuck session to a person mid-task
- Give several agents isolated browsers under one key
- Record a browser session for review

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http cloud-browser https://scrappy.gg/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://scrappy.gg/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "cloud-browser": {
      "url": "https://scrappy.gg/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "cloud-browser": {
      "type": "http",
      "url": "https://scrappy.gg/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "cloud-browser": {
      "serverUrl": "https://scrappy.gg/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "cloud-browser": {
      "type": "http",
      "url": "https://scrappy.gg/api/mcp"
    }
  }
}
```

## FAQ

### How do I connect Claude Code?

Run claude mcp add --transport http scrappy https://scrappy.gg/api/mcp with an Authorization Bearer header holding your API key.

### How is it different from a local browser MCP server?

A local one drives a browser on your machine from your IP; this one runs in the cloud on a residential exit, keeps logins and has a live viewer.

### What does a session cost?

5 credits to start and 1 credit per minute, with the residential proxy included.

### Can I try it free?

New accounts get 100 credits with no card.

### Does it bypass site protections?

It detects CAPTCHAs and offers human takeover; scraping remains subject to each site's terms and robots.txt.

### Is Scrappy Cloud Browser free?

No. Scrappy Cloud Browser is a paid product.

### How do I add Scrappy Cloud Browser to Claude Code?

Run this command in your terminal: claude mcp add --transport http cloud-browser https://scrappy.gg/api/mcp

### What are the best alternatives to Scrappy Cloud Browser?

The closest alternatives to Scrappy Cloud Browser are Browser Use, Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search and Oya Browser.

## Alternatives

- [Browser Use](https://ai-powered.com/mcp/browser-use): Browser Use is a freemium MCP server for browser automation.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [Mantis](https://ai-powered.com/mcp/mantis-2): Mantis is an open-source MCP server for browser automation.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/scrappy-cloud-browser
