Advertise
MCP.so
Sign In

Scrappey MCP Server

@pim97

Repository

Basic information

Category

Other

Transports

stdio

Author

pim97

About Scrappey MCP Server

Allow LLMs to control a browser with Scrappey

Scrappey MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-scrappey": {
      "command": "npx",
      "args": [
        "@anthropic/smithery-cli",
        "deploy"
      ]
    }
  }
}

Scrappey MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Scrappey MCP Server?

A Model Context Protocol server for interacting with Scrappey.com's browser-backed web automation and data-extraction platform. It bridges AI models with real browser sessions to handle JavaScript-dependent pages, challenge pages from bot-management systems (Cloudflare, Datadome, Kasada, etc.), and interactive captchas.

How to use Scrappey MCP Server?

Install via npm install and npm run build, then set the SCRAPPEY_API_KEY environment variable. Configure Claude Desktop or Cursor IDE with the server’s path and API key. Use tools like scrappey_create_session, scrappey_request, scrappey_browser_action, and scrappey_screenshot to create sessions, send browser-backed HTTP requests, execute automation actions, and take screenshots.

Key features of Scrappey MCP Server

  • Creates and manages persistent browser sessions
  • Sends HTTP requests through browser-backed infrastructure
  • Executes browser actions (click, type, scroll, etc.)
  • Renders JavaScript challenge pages from major bot-management systems
  • Solves interactive captcha widgets (Turnstile, reCAPTCHA, hCaptcha)
  • Takes screenshots and records video

Use cases of Scrappey MCP Server

  • Testing and monitoring applications you own or operate
  • Collecting data you are authorized to access from JavaScript-heavy websites
  • Automating interactions on pages protected by Cloudflare, Akamai, or Datadome
  • Extracting structured content using CSS selectors and browser actions

Frequently asked questions

1

What do I need to use this server?

A Scrappey API key from scrappey.com and Node.js installed.

2

How does it handle Cloudflare and other challenge pages?

Scrappey renders challenge pages in a real browser; you can enable bypass per request with fields like `cloudflareBypass`, `datadomeBypass`, and `kasadaBypass`.

3

Can I reuse browser sessions?

Yes, sessions persist cookies and state across requests. Reuse sessions for related work and destroy them when finished.

4

What proxies are supported?

You can specify a custom proxy, proxy country, premium proxy, or mobile proxy. Supported countries include UnitedStates, UnitedKingdom, Germany, France, and more.

5

Are there any limits or error codes?

Session limits are shown in the list response. Error codes (e.g., CODE-0001 for capacity full, CODE-0029 for too many sessions) provide specific failure details.

Comments

More Other MCP servers

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

ICSS

chokcoco

不止于 CSS

20.7K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
Advertise