Apify MCP Server

Apify provides cloud-based web scraping and automation through reusable "Actors" — containerized scrapers for extracting data from websites at scale. The platform includes pre-built scrapers for popular sites like Amazon, Google, and social media platforms, plus infrastructure for running custom scraping workflows.

Core Capabilities

Actor Discovery & Execution: Search the Apify Store to find scrapers for specific platforms or use cases, get detailed information about available Actors including their input schemas, and execute any Actor with custom parameters.

Run Management & Results: Monitor Actor execution by checking run status, timestamps, and metadata. Retrieve output datasets from completed runs with field selection for targeted data extraction.

Documentation Access: Full-text search across Apify and Crawlee documentation to find implementation guidance, plus direct access to complete documentation pages.

Specialized Web Browsing: Dedicated RAG-enabled web browser Actor for intelligent content extraction and question-answering from web pages.

Domain Model

Actors are the core abstraction — containerized scraping tools with defined input schemas and output formats. Each execution creates a Run with associated metadata and a Dataset containing structured results. The Store serves as a marketplace of community and official Actors.

Key Workflows

Always fetch Actor details first to understand required inputs before execution. Use the search functionality to discover appropriate scrapers for your use case rather than building from scratch. Monitor run status before attempting to retrieve results.