Skip to main content
ScrayleScrayle
Model Context Protocol Server

Give Your AI Agent
Real Scraping Power

Connect Claude, Cursor, ChatGPT, VS Code, or any MCP-compatible AI agent to 33 web scraping and automation tools. Scrape, crawl, run browser sessions, and execute workflows — all from your AI chat.

33Tools
7Categories
Streamable HTTPProtocol

See It In Action

Your AI agent calls Scrayle tools naturally during conversation.

Scrayle MCP Server
>

MCP Server URL

Copy this URL and paste it into your AI client to connect.

https://mcp.scrayle.com/mcp

Authentication required. Use your Scrayle API key as a Bearer token or x-api-key header.

33 Tools, 7 Categories

Every Scrayle capability exposed as an MCP tool. Your AI agent discovers and calls them automatically.

Scraping
2 tools
scrape_url

Scrape a single web page and extract its content as markdown, HTML, or structured data.

batch_scrape

Scrape multiple web pages at once. Ideal for lists of URLs, search results, or product pages.

Crawling
2 tools
crawl_website

Crawl a website following links to discover and scrape multiple pages from a starting URL.

cancel_crawl

Cancel a running crawl job by its ID.

Browser Control
12 tools
start_browser_session

Launch a cloud browser with anti-detection and stealth. Returns a session your AI controls directly.

browser_navigate

Navigate the browser to any URL and get the page title.

browser_click

Click elements on the page by CSS selector.

browser_type

Type text into input fields with optional Enter key press.

browser_screenshot

Take a screenshot of the current page to see what it looks like.

browser_get_content

Extract visible text from the page or a specific element.

browser_evaluate

Execute JavaScript in the browser for custom interactions.

browser_select

Select options from dropdown menus.

browser_scroll

Scroll the page up or down.

browser_wait

Wait for elements to appear or the page to finish loading.

close_browser_session

Close an active cloud browser session and disconnect.

list_browser_profiles

List saved browser profiles with persistent cookies and fingerprints.

Workflows
5 tools
create_workflow

Create a new automation workflow with nodes, edges, and data extraction steps.

list_workflows

List all your saved automation workflows.

run_workflow

Execute a pre-built automation workflow with custom input parameters.

get_workflow_status

Check the status of a running or completed workflow.

list_workflow_runs

List recent workflow runs with their status and results.

Marketplace
3 tools
search_marketplace

Search for pre-built scraping workflows and automation actors.

get_marketplace_actor

Get detailed info about a marketplace actor including input schema.

run_marketplace_actor

Run a marketplace actor with custom input parameters.

CAPTCHA
1 tool
solve_captcha

Solve CAPTCHA challenges - ReCaptcha, hCaptcha, Turnstile, Cloudflare.

Storage
8 tools
kv_create_namespace

Create a new key-value store namespace for persistent data storage.

kv_get

Get a value from a key-value store.

kv_set

Store a value in a key-value store.

kv_list_namespaces

List all key-value store namespaces.

create_dataset

Create a new dataset for storing structured records.

list_datasets

List all datasets with item counts.

get_dataset_items

Retrieve items from a dataset.

add_dataset_items

Add items to a dataset.

Connect Your AI Client

Choose your AI client for setup instructions. One-click install available for supported clients.

1{
2  "mcpServers": {
3    "scrayle": {
4      "url": "https://mcp.scrayle.com/mcp",
5      "headers": {
6        "x-api-key": "YOUR_SCRAYLE_API_KEY"
7      }
8    }
9  }
10}
Fastest path

One-click install

Opens Cursorand adds Scrayle to your MCP servers for you. You'll still need to paste your API key the first time a tool is called.

Install in Cursor
Manual setup · Cursor
  1. 1Open Cursor Settings (Cmd/Ctrl + ,)
  2. 2Go to "MCP Servers" in the sidebar
  3. 3Click "Add MCP Server" and paste the JSON config below
  4. 4Replace YOUR_SCRAYLE_API_KEY with your actual API key
  5. 5Restart Cursor to activate

What's Next?

Once you're connected to the Scrayle MCP Server, try asking your agent:

What Scrayle tools are available and what can I do with them?

Your agent will discover all 33 tools across 7 categories and suggest what you can do with them.

How It Works

🔑
Step 1

Sign Up & Get API Key

Create a free Scrayle account and generate an API key from the dashboard.

🔌
Step 2

Connect Your AI Client

Add the Scrayle MCP server to Cursor, Claude, VS Code, or any MCP client.

🚀
Step 3

Ask Your Agent to Scrape

Just type "scrape this website" or "crawl these pages" and your AI handles the rest.

Frequently Asked Questions

Everything you need to know about Scrayle MCP.

What is the Scrayle MCP server?
The Scrayle MCP server is a Model Context Protocol (MCP) server that connects any MCP-compatible AI client - Claude, Cursor, VS Code, Windsurf, ChatGPT - to 35 fully managed web scraping and browser automation tools. Your AI agent can scrape websites, run headless browsers, execute workflows, and extract structured data directly from chat.
Which AI clients are compatible with Scrayle MCP?
Scrayle MCP works with any MCP-compatible client: Claude Desktop, Claude.ai, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, ChatGPT, and OpenAI Codex. Cursor and VS Code support one-click installation. Other clients connect using the MCP server URL with your Scrayle API key.
Is the Scrayle MCP server free?
Yes. Every new Scrayle account includes a free starter wallet balance — no payment card required. Sign up, generate an API key, and add the MCP server URL to start scraping from your AI agent immediately.
What web scraping tools are available in Scrayle MCP?
Scrayle MCP exposes 35 tools across 7 categories: URL scraping, batch scraping, web crawling, full browser session management (Playwright/Puppeteer compatible), workflow execution, dataset and key-value storage, and web search. Your AI agent auto-discovers and calls them naturally during conversation.
How do I connect Scrayle MCP to Claude Desktop?
Open your claude_desktop_config.json file and add Scrayle to the mcpServers section with the URL https://mcp.scrayle.com/mcp and your Scrayle API key as the x-api-key header. Save the file and restart Claude Desktop to activate the connection.
What is the Scrayle MCP server URL?
The Scrayle MCP server URL is https://mcp.scrayle.com/mcp. It uses Streamable HTTP transport. Authenticate using your Scrayle API key as a Bearer token in the Authorization header, or as the value of the x-api-key header.
Does Scrayle MCP support browser automation?
Yes. Scrayle MCP includes tools for launching full Chromium browser sessions compatible with Playwright and Puppeteer, with built-in anti-bot bypass, JavaScript rendering, residential proxy rotation, and persistent browser profiles for authenticated scraping at scale.
Can AI agents schedule and automate recurring scraping jobs with Scrayle MCP?
Yes. Through the workflow tools, your AI agent can create, run, and schedule visual automation workflows with cron scheduling. Results can be delivered via webhook or email, and datasets are stored in Scrayle's built-in storage - all accessible through MCP tools.

More Ways to Integrate

Go beyond MCP with our SDK, REST API, and documentation.

Documentation

Full guides, API reference, and tutorials for every tool.

GitHub

Open-source SDK, examples, and community contributions.

REST API

Direct HTTP access to all scraping and automation endpoints.

Discord

Join our community for support, tips, and feature requests.

Ready to Give Your AI Agent Scraping Superpowers?

Start with a free wallet balance. No payment card required.