apify-mcp-server: an MCP server that connects AI agents to thousands of ready-made web scrapers and automation tools

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, maps, and e-commerce sites.

How it works

The server acts as an interface between an MCP-compatible client (like Claude Desktop or VS Code) and the Apify platform. It dynamically converts Apify Actors into tools that an AI agent can discover and execute. The server can be deployed as a hosted HTTPS endpoint or run locally via standard input/output (stdio).

Key operational features include:

• Dynamic Tool Discovery: Agents can search for and fetch details about new Actors to use them as tools on the fly.
• Schema Inference: The server loads an Actor's input schema so the LLM knows exactly what arguments to provide.
• Agentic Payments: Supports machine-to-machine payments via x402 (USDC on Base) and Skyfire, allowing agents to pay for Actor runs without a traditional API token.

Who it’s for

Developers and AI researchers using MCP-compatible clients (such as Claude.ai, Cursor, or VS Code) who want their AI assistants to have the ability to scrape the web, extract structured data, and automate browser-based tasks.

Highlights

• Massive Tool Library: Access to over 8,000 Apify Actors for diverse web data extraction.
• Flexible Deployment: Available as a hosted server (mcp.apify.com) or a local npx package.
• Integrated Payments: Native support for x402 and Skyfire for autonomous agent funding.
• Broad Compatibility: Works with Claude Code, Claude.ai, Cursor, VS Code, and other MCP-compliant clients.
• Helper Tools: Includes built-in tools for searching Apify documentation and managing Actor runs and storage.