apify/apify-mcp-server

The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

What it solves

This project provides a Model Context Protocol (MCP) server that allows AI agents to access thousands of ready-made web scraping, crawling, and automation tools (called "Actors") from the Apify Store. It bridges the gap between LLMs and real-world web data extraction from social media, search engines, and e-commerce sites.

How it works

The server implements the Model Context Protocol, enabling AI assistants to discover and execute Apify Actors as tools. It can be deployed as a hosted HTTPS endpoint or run locally via standard input/output (stdio). The server dynamically loads an Actor's input schema so the LLM knows exactly what arguments to provide. It also includes helper tools for searching the Apify Store, reading documentation, and managing Actor runs and storage.

Who it’s for

Developers and AI agent builders using MCP-compatible clients (such as Claude Desktop, Cursor, or VS Code) who need their agents to perform complex web data extraction and automation tasks.

Highlights

  • Dynamic Tool Discovery: Agents can search for and integrate new Actors from the Apify Store on the fly.
  • Agentic Payments: Supports machine-to-machine payments via x402 (USDC on Base) and Skyfire, allowing agents to pay for Actor runs without an API token.
  • Broad Compatibility: Works with any MCP-compliant client, including Claude.ai and various IDEs.
  • Flexible Deployment: Available as a hosted server for easy setup or a local CLI tool for deeper integration.