Apify

This is Apify’s official MCP Server that enables your AI assistants to access 8,000+ web scraping, data extraction, and automation tools.

It can scrape social media, extract contact information, search the web, and automate virtually any web-based task using pre-built Actors from the Apify Store.

More Features

  • 🔧 Dynamic Tool Discovery: AI agents can search for and add new Actors as needed during conversations.
  • 🌐 Multiple Deployment Options: Choose between hosted service at mcp.apify.com or local stdio server.
  • 🔌 MCP Client Compatibility: Works with Claude Desktop, VS Code, Cursor, and other MCP clients.
  • 📊 Complete Data Access: Retrieve datasets, key-value stores, and run logs from the Apify platform.
  • 🔍 Documentation Integration: Search and fetch Apify documentation directly within conversations.

Use Cases

  • Competitive Intelligence: Monitor social media posts, track pricing changes, and gather market research data automatically.
  • Lead Generation: Extract contact details from business directories and Google Maps listings at scale.
  • Content Aggregation: Collect news articles, blog posts, and social media content for analysis.
  • Research Automation: Perform comprehensive web searches and extract structured data from multiple sources.
  • Data Pipeline Integration: Feed real-time web data into your existing analytics and business intelligence systems.

Install the MCP Server

Prerequisites

  • Apify API Token: You need an account on Apify and an API token.
  • Node.js: Version 18 or higher (for local installation).
  • MCP Client: An AI assistant like Claude Desktop, VS Code (with Genie extension), or Cursor.

Method 1: Using the Hosted Server (Recommended)

The hosted version is accessible at https://mcp.apify.com. It supports OAuth, making it compatible with clients like Claude.ai.

You can configure which tools are loaded by appending query parameters to the URL.

  • Default setup (Actors, Docs, Web Browser):
    https://mcp.apify.com
  • Specific Actor only:
    https://mcp.apify.com?tools=apify/instagram-scraper
  • Disable Telemetry:
    https://mcp.apify.com?telemetry-enabled=false

Method 2: Local Installation (Stdio)

1. Set your API token and run the server.

export APIFY_TOKEN="your_token_here"
npx @apify/actors-mcp-server

2. Add the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": [
        "-y",
        "@apify/actors-mcp-server"
      ],
      "env": {
        "APIFY_TOKEN": "your_apify_token_here"
      }
    }
  }
}

3. Customize the local server behavior using flags:

  • --tools <list>: Specify tools or categories (e.g., --tools actors,docs).
  • --telemetry-enabled=false: Disable data collection.

Available Tools and Functions

  • search-actors: Searches the Apify Store for relevant Actors.
  • fetch-actor-details: Retrieves metadata and input schema for a specific Actor.
  • call-actor: Executes an Actor run and returns a preview of the results. (Default for static clients).
  • add-actor: (Experimental) Adds an Actor as a tool dynamically during a session. (For dynamic clients).
  • apify-slash-rag-web-browser: A pre-configured Actor tool specifically for web browsing and RAG tasks.
  • get-actor-output: Retrieves the full output of a run. Essential when call-actor returns truncated data.
  • get-actor-run: specific details about a single execution.
  • get-actor-run-list: Lists runs for an Actor, filterable by status.
  • get-actor-log: Fetches the console logs for a specific run (useful for debugging).
  • get-dataset: Gets metadata about a specific dataset.
  • get-dataset-items: Retrieves actual data items from a dataset (supports pagination).
  • get-dataset-schema: Generates a JSON schema based on the items in a dataset.
  • get-dataset-list: Lists all available datasets for the user.
  • get-key-value-store: Gets metadata about a specific key-value store.
  • get-key-value-store-keys: Lists keys within a store.
  • get-key-value-store-record: Retrieves the value associated with a specific key.
  • get-key-value-store-list: Lists all available key-value stores.
  • search-apify-docs: Searches the official Apify documentation.
  • fetch-apify-docs: Fetches the full content of a documentation page.

Latest MCP Servers

YouTube MCP Server

Connect your AI agent to YouTube with this MCP server. Supports 99 languages, in-memory audio processing, and efficient caching for developers.

SEO Research

Integrate Ahrefs SEO data into your IDE with SEO Research MCP. Check backlinks, traffic, and keywords directly in Cursor, Claude, and VS Code.

Cursor n8n

Control your n8n workflows directly from Cursor IDE. This MCP server enables AI assistants to create, manage, and debug automations via the n8n API.

View More MCP Servers >>

Featured MCP Servers

Apify

Connect AI assistants to 8000+ web scraping tools via Apify MCP Server. Extract social media data, contact details, and automate web research.

Blueprint

Use the Blueprint MCP Server to generate system architecture diagrams directly from your codebase using Nano Banana Pro.

Monday.com

Use the monday.com MCP server to connect AI agents to your Work OS. Provides secure data access, action tools, and workflow context.

More Featured MCP Servers >>

FAQs

Q: What exactly is the Model Context Protocol (MCP)?

A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.

Q: How is MCP different from OpenAI's function calling or plugins?

A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.

Q: Can I use MCP with frameworks like LangChain?

A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.

Q: Why was MCP created? What problem does it solve?

A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.

Q: Is MCP secure? What are the main risks?

A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.

Q: Who is behind MCP?

A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.

Get the latest & top AI tools sent directly to your email.

Subscribe now to explore the latest & top AI tools and resources, all in one convenient newsletter. No spam, we promise!