-
securityA
license-
qualityEmpowers AI agents to perform web browsing, automation, and scraping tasks with minimal supervision using natural language instructions and Selenium.
Last updated -
4
Apache 2.0
Scrappey MCP Server
A Model Context Protocol (MCP) server for interacting with Scrappey.com's web automation and scraping capabilities. Try it out directly at smithery.ai/server/@pim97/mcp-server-scrappey.
Overview
This MCP server provides a bridge between AI models and Scrappey's web automation platform, allowing you to:
Create and manage browser sessions
Send HTTP requests through Scrappey's infrastructure
Execute browser actions (clicking, typing, scrolling, etc.)
Handle various anti-bot protections automatically
Setup
Get your Scrappey API key from Scrappey.com
Set up your environment variable:
SCRAPPEY_API_KEY=your_api_key_here
Available Tools
1. Create Session (scrappey_create_session)
Creates a new browser session that persists cookies and other state.
{
"proxy": "http://user:pass@ip:port" // Optional: Custom proxy, leave empty for default
}
2. Destroy Session (scrappey_destroy_session)
Properly closes a browser session.
{
"session": "session_id_here" // Required: The session ID to destroy
}
3. Send Request (scrappey_request)
Send HTTP requests through the Scrappey infrastructure.
{
"cmd": "request.get", // Required: request.get, request.post, etc.
"url": "https://example.com", // Required: Target URL
"session": "session_id_here", // Required: Session ID to use
"postData": "key=value", // Optional: POST data
"customHeaders": { // Optional: Custom headers
"User-Agent": "custom-agent"
}
}
4. Browser Actions (scrappey_browser_action)
Execute browser automation actions.
{
"session": "session_id_here", // Required: Session ID to use
"browserActions": [ // Required: Array of actions to perform
{
"type": "click", // Action type: click, hover, type, scroll, wait
"cssSelector": ".button", // CSS selector for element
"text": "Hello", // Text to type (for type action)
"wait": 1000 // Wait time in ms
}
]
}
Typical Workflow
Create a session:
{
"name": "scrappey_create_session"
}
Use the returned session ID for subsequent requests:
{
"name": "scrappey_request",
"cmd": "request.get",
"url": "https://example.com",
"session": "returned_session_id"
}
Perform browser actions if needed:
{
"name": "scrappey_browser_action",
"session": "returned_session_id",
"browserActions": [
{
"type": "click",
"cssSelector": "#login-button"
},
{
"type": "type",
"cssSelector": "#username",
"text": "myuser"
}
]
}
Clean up by destroying the session when done:
{
"name": "scrappey_destroy_session",
"session": "returned_session_id"
}
Features
Session persistence for maintaining state
Automatic anti-bot protection handling
Support for custom proxies
Browser automation capabilities
HTTP request methods (GET, POST, PUT, DELETE, PATCH)
Custom headers and cookies support
Best Practices
Always destroy sessions when you're done with them
Reuse sessions when making multiple requests to the same site
Use appropriate wait times between actions for more human-like behavior
Check if a session exists before using it
Error Handling
The server will return error messages with details when something goes wrong. Common errors include:
Invalid session IDs
Network timeouts
Invalid selectors for browser actions
Anti-bot protection failures
Resources
License
MIT License
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A server that bridges AI models with Scrappey's web automation platform, allowing creation of browser sessions, execution of HTTP requests, and automation of browser actions while handling anti-bot protections.
Related MCP Servers
- AsecurityAlicenseAqualityA Model Context Protocol server enabling AI assistants to scrape web content with high accuracy and flexibility, supporting multiple scraping modes and content formatting options.Last updated -4142MIT License
- -securityFlicense-qualityHigh-performance server enabling AI assistants to access web scraping, crawling, and deep research capabilities through Model Context Protocol.Last updated -16
- AsecurityFlicenseAqualityAn MCP server that enables AI assistants to capture and analyze web page screenshots using Puppeteer, supporting multi-breakpoint captures, error reporting, and page interactions.Last updated -1277