A curated collection of production-ready Model Context Protocol (MCP) servers published on Apify. These are wrappers around open-source MCP servers — credits go to the original developers.
- Monetize your MCP servers via pay-per-use pricing
- Reach a global developer and business audience
- Reliable hosting, scaling, and monitoring
- Built-in analytics
- Community exposure via Apify MCP server and the Apify Store
- Standby mode for instant responses
- Multi-transport (http-streamable and SSE) support
- OAuth for easy authentication
| Actor | Description | Actor badge | Original author |
|---|---|---|---|
| Brave Search MCP Server | Web search capabilities powered by Brave Search | MCP Community | |
| Perplexity Sonar MCP Server | AI-powered search and information retrieval | Perplexity AI | |
| Firecrawl MCP Server | Web crawling and content extraction | Mendable AI | |
| Slide Speak MCP Server | Presentation and speech synthesis | SlideSpeak | |
| Lara Translate MCP Server | Multi-language translation services | Translated | |
| Calculator MCP Server | Mathematical computations and calculations | Githejie | |
| National Parks MCP Server | Geographic and park information | KyrieTangSheng |
These are wrappers—original code by: Brave Software, Perplexity AI, Mendable AI, SlideSpeak, Translated, Githejie, KyrieTangSheng, and others.
🚩 Claim this MCP server – If you are the original developer and would like to claim ownership or have any concerns, please write to [email protected].
- For TypeScript servers: Node.js 18+ and npm
- For Python servers: Python 3.8+ and pip
- For all servers: Docker (optional, for containerized deployment)
Each server can be installed and run independently:
# TypeScript servers
cd <server-name>
npm install
npm start
# Python servers
cd <server-name>
pip install -r requirements.txt
python -m src.mainConfigure your MCP client (like Claude Desktop) to use these servers:
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": ["-y", "@apify/brave-search-mcp-server"]
},
"calculator": {
"command": "python",
"args": ["-m", "src.main"],
"cwd": "./calculator-MCP-server"
}
}
}When creating new MCP servers, you can use our pre-built templates:
- Python MCP server template - For Python-based MCP servers
- TypeScript MCP server template - For TypeScript-based MCP servers
mcp-servers/
├── <server-name>/
│ ├── src/ # Source code
│ ├── Dockerfile # Container configuration
│ ├── package.json # Node.js dependencies (TypeScript servers)
│ ├── requirements.txt # Python dependencies (Python servers)
│ └── README.md # Server-specific documentation
├── LICENSE # MIT License
├── CONTRIBUTING.md # Contribution guidelines
├── README.md # This file
This monorepo is maintained by Apify. We encourage you to build your own MCP servers using our templates—see the official MCP documentation and Apify MCP docs.
To report issues or request features, open an issue with details.
The Apify Model Context Protocol (MCP) Server at mcp.apify.com instantly connects AI applications and agents to thousands of ready-built tools. It allows your AI assistant to use any Apify Actor for web scraping, data extraction, and automation tasks in real time.
Key benefits:
- Instant access to 5,000+ Apify Actors and tools
- No setup required - connect with just a URL
- OAuth support for easy authentication
- Production-ready with enterprise-grade reliability
For the easiest setup and most powerful features, connect your AI assistant to our hosted server:
It supports OAuth, so you can connect from clients like Claude.ai or Visual Studio Code with just the URL.
Learn how to build and monetize MCP servers on Apify:
- Webinar: Building and Monetizing MCP Servers on Apify
- How to build and monetize an AI agent on Apify
- What is MCP and why does it matter?
Made with ❤️ and 🍺 by the Apify team