Apify MCP
Give agents access to thousands of ready-made web scrapers and crawlers
Last verified: August 2, 2026
How to Install Apify MCP
$npx @apify/actors-mcp-server@latestRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
About Apify MCP
The official Apify MCP server lets AI agents extract data from social media, search engines, maps, e-commerce, and virtually any website using thousands of ready-made scrapers ('Actors') from the Apify Store. It turns Apify's automation platform into a tool layer agents can call directly, with a hosted endpoint at mcp.apify.com or local install.
Apify MCP is a Browser Automation MCP server designed for QA, growth, ops, and research teams. It enables driving a real browser from an AI assistant by exposing Playwright/Puppeteer sessions as MCP tools. Key capabilities include navigate, click, type, and submit, headless screenshots and pdfs, form-fill and file-upload flows, and structured tool calls that work cleanly inside an LLM context. It integrates with Playwright, Puppeteer, headless Chromium, and Selenium grids, and is best suited for QA, growth, ops, and research teams who need end-to-end testing.
Key Features
- web scraping
- data extraction
- crawling
- automation
- Navigate, click, type, and submit
- Headless screenshots and PDFs
Pricing
- Core MCP server
- Community support
- Works with any MCP client
- Everything in Free
- Higher usage limits
- Priority support
- Everything in Pro
- SLA & SSO
- Dedicated support
Tier details are indicative — visit the Apify MCP website for current pricing.
Pros & Cons
Pros
- Reaches sites that don't expose APIs
- Self-healing test flows
- Strong selectors paired with LLM context
Cons
- Slower than direct API calls
- Brittle against aggressive bot protection
- Per-session state can leak without isolation
Best For
- End-to-end testing
- Scraping rendered pages
- Form-heavy workflows
- Dashboard data extraction
Screenshots
Screenshots coming soon —
Submit yours →Our Take on Apify MCP
Apify MCP is the fastest way to give an agent real web-scraping muscle without building scrapers yourself, backed by thousands of maintained Actors. Costs are usage-based, so heavy scraping adds up, but the breadth and reliability are hard to beat.