Apify Model Context Protocol (MCP) Server logo

Apify Model Context Protocol (MCP) Server

by Apify

The Apify MCP Server enables interaction with Apify Actors, allowing AI assistants to use them as tools to perform specific tasks. It can be used as an Apify Actor running on the Apify platform or as a local server.

View on GitHub

Last updated: N/A

What is Apify Model Context Protocol (MCP) Server?

The Apify MCP Server is an implementation of an MCP server for Apify Actors, allowing AI applications to connect to external tools and data sources. It exposes Apify's Actors through the MCP protocol, enabling AI Agents or frameworks to access them for data extraction, web searching, and other tasks.

How to use Apify Model Context Protocol (MCP) Server?

The server can be used in two ways: as an Apify Actor via HTTP Server-Sent Events (SSE) or as a local server via standard input/output (stdio). For the Apify Actor, send HTTP requests with your Apify API token. For local use, configure an MCP client like Claude Desktop or VS Code with the server, providing your Apify API token.

Key features of Apify Model Context Protocol (MCP) Server

  • Enables AI agents to use Apify Actors as tools

  • Supports Server-Sent Events (SSE) and standard input/output (stdio) communication

  • Pre-configured with several Apify Actors

  • Provides helper tools to discover and manage available Actors

  • Integrates with various MCP clients like Claude Desktop, VS Code, and LibreChat

Use cases of Apify Model Context Protocol (MCP) Server

  • Extracting data from Facebook posts

  • Extracting Google Maps contact details

  • Scraping Google Search Engine Results Pages (SERPs)

  • Scraping Instagram posts, profiles, places, photos, and comments

  • Searching the web and scraping content from URLs

FAQ from Apify Model Context Protocol (MCP) Server

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) allows AI applications to connect to external tools and data sources in a secure and controlled manner.

How is the MCP Server related to AI Agents?

The Apify MCP Server exposes Apify's Actors through the MCP protocol, allowing AI Agents to access them as tools for various tasks.

What Apify Actors can I use with the MCP Server?

Any Apify Actor can be used, but the server is pre-configured with Actors like Instagram Scraper, RAG Web Browser, and Google Maps Email Extractor. You can also specify a different set of Actors.

How do I interact with the MCP Server?

You can interact with the server using MCP clients such as Claude Desktop, Visual Studio Code, LibreChat, or the Apify Tester MCP Client.

What if I encounter issues while using the MCP Server?

Ensure you have Node.js installed, the APIFY_TOKEN environment variable set, and are using the latest version of the MCP server. You can also submit an issue in Apify Console for further assistance.