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 r
What is 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.
Overview of apify-mcp-server
What it is
The Apify MCP Server is a Model Context Protocol server hosted at mcp.apify.com that allows AI agents to use thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store. It supports OAuth, enabling connection from clients like Claude.ai or Visual Studio Code using just the URL. The server is compatible with Claude Code, Claude.ai, Cursor, VS Code and any client that adheres to the Model Context Protocol. It also supports agentic payments via AGI, direct x402, or Skyfire. Legacy SSE transport has been removed in favor of Streamable HTTP.
Key features
- AI assistants can use any Apify Actor as a tool to perform specific tasks, such as scraping Facebook posts, Google Maps data, search engine results, Instagram content, or general web fetching.
- Supports two connection methods: HTTPS endpoint (
https://mcp.apify.com) with OAuth or Bearer token authentication, or Standard Input/Output (stdio) for local integrations vianpx @apify/actors-mcp-server. - Provides agentic payment options: AGI (prepaid token), direct x402 (USDC on Base), or Skyfire (PAY tokens).
- Dynamic tool discovery and output schema inference for structured Actor results (in the hosted server).
- Tested with multiple clients including Claude Desktop, Claude.ai, ChatGPT, VS Code (Genie), Cursor, OpenCode, Kiro, and the Apify Tester MCP Client.
Use cases
- Extracting data from social media platforms (Facebook posts, Instagram content).
- Scraping Google Maps for contact details and business information.
- Retrieving Google Search Engine Results Pages (SERPs) for SEO or research.
- Crawling and fetching content from any website, with JavaScript rendering and anti-bot protection.
- Integrating with AI assistants to automate web data extraction and processing tasks.
Getting started
To use the hosted server, connect via OAuth from any MCP client using the URL https://mcp.apify.com (Streamable HTTP transport). Include the Authorization: Bearer header or use OAuth. For local stdio setup, set the MCP client server command to: bash npx @apify/actors-mcp-server Set the APIFY_TOKEN environment variable to your Apify API token. See npx @apify/actors-mcp-server --help for more options.
License and pricing
The license is MIT. The pricing type is open source. The server supports agentic payments: AGI (recommended), direct x402, or Skyfire, but specific pricing for Actor runs is not stated in the README.
Based on the project's public README and repository metadata.