# Apify MCP Server

> MIT Apify Store MCP — agents scrape via thousands of Actors

**Category:** AI Agents  
**Pricing:** freemium  
**URL:** https://mcp.apify.com  
**GitHub:** https://github.com/apify/apify-mcp-server  
**Added:** 2026-10-02

---

## The Hook

Apify’s MCP server lets agents pull structured data from the web through thousands of Apify Store Actors — hosted at mcp.apify.com or run locally via `@apify/actors-mcp-server`.

## What's Good

MIT (apify/apify-mcp-server). npm `@apify/actors-mcp-server` (HTTP 200). Hosted Streamable HTTP MCP with OAuth for Claude/Cursor/VS Code-class clients; local stdio path for the same Actor toolkit. Covers social, search, maps, e-commerce, and generic site Actors without writing every scraper yourself.

## The Catch

Actor runs and Apify platform usage are billed — the MCP server is MIT, the data path is freemium/paid compute. Vs playwright-mcp / browser-use / firecrawl-class scrapers: those drive browsers or crawl APIs you own — Apify MCP’s catch is Store Actors as MCP tools. Legacy `/sse` endpoint removed — point clients at https://mcp.apify.com; pin which Actors agents may call.

## Verdict

MIT Apify Store MCP when agents need Actor-scale scraping — not Playwright browser MCP alone; budget Apify compute, not just the license.