Apify MCP Server

🚀 Apify Model Context Protocol (MCP) Server

The Apify Model Context Protocol (MCP) server at mcp.apify.com empowers your AI agents to extract data from social media, search engines, maps, e - commerce sites, and other websites. It leverages thousands of ready - made scrapers, crawlers, and automation tools from the Apify Store. The server also supports OAuth, enabling connections from clients like Claude.ai or Visual Studio Code using just the URL. Additionally, it supports Skyfire agentic payments, allowing AI agents to pay for Actor runs without an API token. The Apify MCP Server is compatible with Claude Code, Claude.ai, Cursor, VS Code, and any client adhering to the Model Context Protocol.

🚀 Quick Start

There are two ways to use the Apify MCP Server:

HTTPS Endpoint

Use https://mcp.apify.com and include the <APIFY_TOKEN> header in your requests. This is the recommended method for most scenarios. Since it supports OAuth, you can connect from clients such as Claude.ai or Visual Studio Code using just the URL: https://mcp.apify.com.

• https://mcp.apify.com offers streamable transport.

Standard Input/Output (stdio)

Ideal for local integrations and command - line use. Set the MCP client server command to npx @apify/actors-mcp-server and the APIFY_TOKEN environment variable to your Apify API token.

• See npx @apify/actors-mcp-server --help for more options.

You can find detailed setup instructions in the Apify documentation.

✨ Features

Data Extraction from Multiple Sources

The server allows AI agents to use various tools from the Apify Store to extract data from different types of websites, such as:

• Use Facebook Posts Scraper to extract data from Facebook posts.
• Use Google Maps Email Extractor to get contact details from Google Maps.
• Use Google Search Results Scraper to scrape Google Search Engine Results Pages (SERPs).
• Use Instagram Scraper to scrape Instagram posts, profiles, etc.
• Use RAG Web Browser to search the web and retrieve content.

Video Tutorial

Integrate 8,000+ Apify Actors and Agents with Claude

Compatibility

The Apify MCP Server is compatible with any MCP client adhering to the Model Context Protocol. You can use clients like Claude Desktop, Visual Studio Code, or Apify Tester MCP Client.

Skyfire Agentic Payments

It integrates with Skyfire to enable AI agents to pay for Actor runs without an Apify API token.

Dynamic Tool Discovery

The server provides a way to dynamically discover and use new Actors from the Apify Store.

📦 Installation

Prerequisites

• Node.js (v18 or higher)

Steps

1. Create an environment file, .env, with the following content:

APIFY_TOKEN="your-apify-token"

2. Build the actor-mcp-server package:

npm run build

Start the Server

HTTP Streamable MCP Server

export APIFY_TOKEN="your-apify-token"
export APIFY_META_ORIGIN=STANDBY
apify run -p

Standard Input/Output (stdio) MCP Server

export APIFY_TOKEN="your-apify-token"
npx @modelcontextprotocol/inspector node ./dist/stdio.js

💻 Usage Examples

Using the HTTPS Endpoint

// Example code for making a request using the HTTPS endpoint
// Assume you have a way to set the APIFY_TOKEN header
fetch('https://mcp.apify.com', {
    headers: {
        'APIFY_TOKEN': 'your-apify-token'
    }
})
.then(response => response.json())
.then(data => console.log(data));

Using the stdio Server

# Start the stdio server
export APIFY_TOKEN="your-apify-token"
npx @apify/actors-mcp-server

📚 Documentation

SSE Transport Deprecation

Update your MCP client config before April 1, 2026. The Apify MCP server is dropping Server - Sent Events (SSE) transport in favor of Streamable HTTP, in line with the official MCP spec. Go to mcp.apify.com to update the installation for your client.

MCP Clients

Supported Clients Matrix

Smart Tool Selection

• Clients with dynamic tool support (e.g., Claude.ai web, VS Code Genie): The server provides the add-actor tool instead of call-actor.
• Clients with limited dynamic tool support (e.g., Claude Desktop): The server provides the standard call-actor tool.

Try Apify MCP Instantly

• Use Apify Tester MCP Client to explore the capabilities without local setup.
• Use the MCP bundle file: Apify MCP server MCPB file

Skyfire Agentic Payments

Prerequisites

• A Skyfire account with a funded wallet
• An MCP client that supports multiple servers (e.g., Claude Desktop, OpenCode, VS Code)

Setup

{
    "mcpServers": {
        "skyfire": {
            "url": "https://api.skyfire.xyz/mcp/sse",
            "headers": {
                "skyfire-api-key": "<YOUR_SKYFIRE_API_KEY>"
            }
        },
        "apify": {
            "url": "https://mcp.apify.com?payment=skyfire"
        }
    }
}

How it Works

1. The agent discovers relevant Actors via search-actors or fetch-actor-details (free).
2. Before executing an Actor, the agent creates a PAY token using the create-pay-token tool (minimum $5.00 USD).
3. The agent passes the PAY token in the skyfire-pay-id input property when calling the Actor tool.
4. Results are returned as usual.

Tools, Resources, and Prompts

Actors

Any Apify Actor can be used as a tool. The server is pre - configured with apify/rag - web - browser and several helper tools. For example, for the apify/rag - web - browser Actor:

{
    "query": "restaurants in San Francisco",
    "maxResults": 3
}

Helper Tools

• Apify Actors: Search, view details, and use as AI tools.
• Apify documentation: Search and fetch documents.
• Actor runs: Get run lists, inspect details, and retrieve logs.
• Apify storage: Access dataset and key - value store data.

Overview of Available Tools

Tool Annotations

• title: Short display name for the tool.
• readOnlyHint: true for read - only data tools.
• openWorldHint: true for tools accessing external resources.

Tools Configuration

The tools parameter can be used to specify loaded tools. For example:

https://mcp.apify.com?tools=actors,docs,apify/rag-web-browser

npx @apify/actors-mcp-server --tools actors,docs,apify/rag-web-browser

UI Mode Configuration

Hosted server:

https://mcp.apify.com?ui=true

CLI:

npx @apify/actors-mcp-server --ui true

Backward Compatibility

The v2 configuration is backward - compatible with v1 usage. Some old parameters are still supported but may be deprecated.

Prompts

The server provides predefined example prompts, such as the GetLatestNewsOnTopic prompt for retrieving news using the RAG Web Browser Actor.

Telemetry

The Apify MCP Server collects telemetry data by default. You can opt out by setting the --telemetry - enabled CLI flag to false or the TELEMETRY_ENABLED environment variable to false.

Development

See CONTRIBUTING.md for contribution guidelines and DEVELOPMENT.md for detailed development setup.

Unauthenticated Access

The hosted server allows access without an API token when the tools query parameter includes only search - actors, fetch - actor - details, search - apify - docs, fetch - apify - docs.

Canary PR Releases

To create a canary release, add the beta tag to your PR branch.

Docker Hub Integration

The Apify MCP Server is available on Docker Hub.

🔧 Technical Details

Actor Input Schema Processing

• Descriptions are truncated to 500 characters.
• Enum fields are truncated to a maximum combined length of 2000 characters.
• Required fields are marked with a REQUIRED prefix.
• Nested properties are built for special cases.
• Array item types are inferred.
• Enum values and examples are added to property descriptions.
• Rental Actors are only available on the hosted MCP server.

🐛 Troubleshooting (local MCP server)

• Ensure node is installed (node -v).
• Set the APIFY_TOKEN environment variable.
• Use the latest version of the MCP server (@apify/actors-mcp-server@latest).

Debugging the NPM package

export APIFY_TOKEN="your-apify-token"
npx @modelcontextprotocol/inspector npx -y @apify/actors-mcp-server

🤝 Contributing

• 🐛 Report issues: Open an issue.
• 🔧 Submit pull requests: Fork the repo and submit PRs.
• 📚 Documentation: Improve docs and examples.
• 💡 Share use cases: Contribute examples.

📚 Learn more

• Model Context Protocol
• What are AI Agents?
• What is MCP and why does it matter?
• How to use MCP with Apify Actors
• Tester MCP Client
• Webinar: Building and Monetizing MCP Servers on Apify
• How to build and monetize an AI agent on Apify