==================
/// MCP ///
/// ACT ///
==================
[server:online]
[protocol:ready]actors-mcp-server
by apify
Model Context Protocol (MCP) Server that lets AI assistants run any Apify Actor for web-scraping, data-extraction and automation tasks.
280
33
Enterprise01
Facebook Posts Scraper
Extract data from Facebook posts across multiple pages or profiles
02
Google Maps Email Extractor
Extract contact details, such as emails, from Google Maps results
03
Google Search Results Scraper
Scrape Google Search Engine Results Pages (SERPs)
04
Instagram Scraper
Scrape Instagram posts, profiles, places, photos, and comments
05
apify/rag-web-browser
Search the web, scrape the top N URLs, and return their content for RAG-style workflows
06
docs
Search the Apify documentation and fetch specific documents
07
runs
Retrieve lists of your Actor runs, inspect their details, and obtain logs
08
storage
Access datasets, key-value stores, and their records on Apify
09
preview
Experimental helper tools that are currently in preview mode
Installation
Prerequisites
• Node.js ≥ 18
• npm (or pnpm / yarn)
• An Apify account and API token (APIFY_TOKEN)
• An LLM provider key (e.g. OPENAI_API_KEY) that the server will delegate to
Local installation
1. Clone the repository
git clone https://github.com/apify/actors-mcp-server.git
cd actors-mcp-server2. Install dependencies
npm install3. Build the TypeScript sources
npm run build4. Configure environment variables (create .env or export in shell)
APIFY_TOKEN= <your-apify-token>
OPENAI_API_KEY= <your-openai-key>
PORT=3000 # optional; defaults to 3000
LOG_LEVEL=info # debug, info, warn, error5. Start the server
-e APIFY_TOKEN=$APIFY_TOKEN \
-e OPENAI_API_KEY=$OPENAI_API_KEY \
npm start # runs "node dist/index.js"
Hot-reloading dev mode
npm run dev # ts-node + nodemon
Docker
docker build -t apify/actors-mcp-server .
docker run -p 3000:3000 \
apify/actors-mcp-serverDocumentation
License: Apache License 2.0
Updated 7/30/2025