OfficialVerified

Apify MCP Server

Apify web scraping tools and automation actors integrated directly into AI assistants.

Data last scanned today · Reviewed today

83 1 dangerous tool6 tools★ 2,204TypeScriptMIT

Overview

This server provides a bridge between AI agents and the Apify platform, allowing for the execution of thousands of scrapers and web automation tools. It supports structured result inference and facilitates complex data extraction from social media, e-commerce, and search engines. The system is designed to work across major MCP-compliant environments like Claude and VS Code. It features unique capabilities such as agentic payments via Skyfire and x402, which enable AI agents to perform tasks without requiring a static API token.

Our verdict

With a security score of 50/100, this server is currently classified as high risk. This rating stems from the fact that it is a community-maintained project rather than an official Apify release, and key security aspects like OAuth implementation and read-only mode have not yet been editorially reviewed. It is suitable for users comfortable with third-party integrations, but should be treated with caution in high-sensitivity environments until further audits are completed.

Supports agentic payments through Skyfire and x402
Compatible with Claude, Cursor, and VS Code
Provides access to thousands of ready-made scrapers
Active development with 2204 GitHub stars

Community-maintained rather than official vendor software
OAuth and read-only modes remain unreviewed
Lack of formal editorial security verification

Setup

Claude Desktop

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

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
call-actor	Executes external Actors.	high
search-actors	Searches the Apify platform for Actors.	low
fetch-apify-docs	Fetches Apify documentation content.	low
report-problem	Reports a problem encountered during tool usage.	medium
fetch-actor-details	Fetches details of a specific Actor.	low
search-apify-docs	Searches through Apify documentation.	low

Compatibility

Client	Local	Docker	Remote	Read-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›Should I use the hosted server or run it locally?

The hosted server at https://mcp.apify.com is recommended because it supports advanced features like output schema inference that are not available when running the server locally via stdio.

›How do I authenticate with the hosted Apify MCP server?

You can connect using OAuth or by including an 'Authorization: Bearer <APIFY_TOKEN>' header in your requests.

›Can I still use the /sse endpoint?

No, the legacy SSE transport has been removed. You must configure your client to use the base URL https://mcp.apify.com.

›Is it possible to use Apify Actors without an API token?

Yes, the server supports agentic payments via x402 and Skyfire, allowing you to pay for Actor runs directly.

›What is the command to run the server locally?

For local integrations, set your MCP client server command to 'npx @apify/actors-mcp-server' and provide your Apify API token via the APIFY_TOKEN environment variable.