Apify
Official Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.
Ads
Overview
The Apify Model Context Protocol (MCP) server at mcp.apify.com enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, and any other website using thousands of ready-made scrapers, crawlers, and automation tools from Apify Store. It supports OAuth, allowing you to connect from clients like Claude.ai or Visual Studio Code using just the URL. > 🚀 Use the hosted Apify MCP Server! > > For the best experience, connect your AI assistant to our hosted server at https://mcp.apify.com. The hosted server supports the latest features - including output schema inference for structured Actor results - that are not available when running locally via stdio.
Installation
npx @apify/actors-mcp-server --tools actors,docs,apify/rag-web-browser,apify/web-fetch
Configuration
{
"mcpServers": {
"skyfire": {
"url": "https://api.skyfire.xyz/mcp/sse",
"headers": {
"skyfire-api-key": "<YOUR_SKYFIRE_API_KEY>"
}
}Capabilities
- Search Apify Store
Ask your assistant to find scrapers and automation tools using `search-actors`, then inspect details with `fetch-actor-details`.
- Run any Actor
Have your assistant execute a scrapers like `call-actor` or the preconfigured `apify--rag-web-browser` to extract data from websites, social media, or maps.
- Retrieve run results
Get paginated dataset items with `get-dataset-items` or check run status and logs via `get-actor-run` and `get-actor-log`.
- Manage storage
Access data from datasets and key-value stores using `get-dataset`, `get-key-value-store-record`, and related list tools.
- Create and manage tasks
Save reusable Actor configurations with `create-actor-task`, update them via `update-actor-task`, and publish landing pages with `publish-actor-task`.
- Search Apify documentation
Look up platform docs with `search-apify-docs` and fetch full pages via `fetch-apify-docs` for context.
Tags
- web-scraping
Related MCP servers
Skyvern
OfficialAI-powered browser automation MCP server — navigate sites, fill forms, extract data, and handle logins via Claude Code CLI
Firecrawl
OfficialExtract web data with Firecrawl
Bright Data
OfficialDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Notte
OfficialLeverage Notte Web AI agents & cloud browser sessions for scalable browser automation & scraping workflows