Unleash the Power of AI Agents with UBOS and Apify’s MCP Server

In today’s rapidly evolving landscape of Artificial Intelligence, the ability to seamlessly integrate AI models with real-world data and tools is paramount. UBOS, a full-stack AI Agent Development Platform, empowers businesses to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with their LLM models, and implement sophisticated Multi-Agent Systems. Central to this capability is the Model Context Protocol (MCP), and Apify’s MCP Server acts as a critical bridge, enabling AI models to access and interact with external data sources and tools through Apify Actors.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard designed to streamline how applications provide context to Large Language Models (LLMs). Think of it as a universal translator, allowing AI applications, such as Claude Desktop, to connect to external tools and data sources in a secure, controlled, and standardized manner. MCP facilitates seamless interactions between AI Agents and various resources, whether they are local or remote.

For an in-depth understanding, refer to the Model Context Protocol website or the informative blog post, What is MCP and why does it matter?.

Apify’s MCP Server: Connecting AI Agents to the World

Apify’s MCP Server is a robust implementation of the MCP, specifically designed to expose Apify’s powerful Actors through the protocol. This means that AI Agents or frameworks that adhere to the MCP can leverage Apify Actors as versatile tools for a wide range of tasks, including:

• Data Extraction: Scrape data from websites, social media platforms, and e-commerce sites.
• Web Searching: Perform targeted searches on the web and retrieve relevant content.
• Automation: Automate complex workflows involving web interactions and data processing.

By integrating Apify Actors via the MCP Server, AI Agents gain the ability to perform tasks that would otherwise be impossible, significantly expanding their capabilities and applicability.

Key Features and Use Cases of Apify’s MCP Server

The Apify MCP Server unlocks a plethora of possibilities for AI-driven applications. Here are some compelling use cases:

• Enhanced Data Collection: Use the Facebook Posts Scraper to extract data from multiple Facebook pages or profiles, enabling AI Agents to analyze social media trends and sentiment.
• Lead Generation: Employ the Google Maps Email Extractor to gather contact details from Google Maps, empowering AI Agents to identify potential leads and build targeted marketing campaigns.
• Market Research: Leverage the Google Search Results Scraper to scrape Google Search Engine Results Pages (SERPs), allowing AI Agents to analyze competitor strategies and identify emerging market opportunities.
• Social Media Monitoring: Utilize the Instagram Scraper to scrape Instagram posts, profiles, places, photos, and comments, enabling AI Agents to monitor brand mentions and track influencer activity.
• Web Content Analysis: Integrate the RAG Web Browser to search the web, scrape the top N URLs, and return their content, allowing AI Agents to summarize information and gain insights from online sources.

How to Use Apify’s MCP Server

The Apify MCP Server can be deployed in two primary ways:

1. As an Apify Actor: Running on the Apify platform in Standby mode, the server exposes an HTTP web server that receives and processes requests via Server-Sent Events (SSE).
2. As a Local Server: Running on your machine, allowing you to connect it to AI clients like Claude Desktop via standard input/output (stdio).

Interacting with the MCP Server

Several MCP clients are available to interact with the Apify MCP Server, including:

• Claude Desktop (Stdio support)
• Visual Studio Code (Stdio and SSE support)
• LibreChat (Stdio and SSE support)
• Apify Tester MCP Client (SSE support with Authorization headers)
• Other clients: https://modelcontextprotocol.io/clients and https://glama.ai/mcp/clients

Once you’ve integrated Apify Actors with the MCP server, you can pose questions like:

• “Search the web and summarize recent trends about AI Agents.”
• “Find the top 10 best Italian restaurants in San Francisco.”
• “Find and analyze the Instagram profile of The Rock.”
• “Provide a step-by-step guide on using the Model Context Protocol with source URLs.”
• “What Apify Actors can I use?”

Example: Running the MCP Server as an Apify Actor

To start the server with default Actors, send an HTTP GET request with your Apify API token to:

https://actors-mcp-server.apify.actor?token=<APIFY_TOKEN>

To interact with the server over SSE, initiate the connection with:

curl https://actors-mcp-server.apify.actor/sse?token=<APIFY_TOKEN>

Then, send a message to the server via a POST request:

curl -X POST “https://actors-mcp-server.apify.actor/message?token=<APIFY_TOKEN>&session_id=a1b” -H “Content-Type: application/json” -d ‘{ “jsonrpc”: “2.0”, “id”: 1, “method”: “tools/call”, “params”: { “arguments”: { “searchStringsArray”: [“restaurants in San Francisco”], “maxCrawledPlacesPerSearch”: 3 }, “name”: “lukaskrivka/google-maps-with-contact-details” } }’

Example: Running the MCP Server Locally with Claude Desktop

1. Ensure you have Claude Desktop installed and Developer Mode enabled.
2. Edit the configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%/Claude/claude_desktop_config.json on Windows, or ~/.config/Claude/claude_desktop_config.json on Linux).
3. Add the following configuration:

{ “mcpServers”: { “actors-mcp-server”: { “command”: “npx”, “args”: [“-y”, “@apify/actors-mcp-server”], “env”: { “APIFY_TOKEN”: “your-apify-token” } } } }

4. Restart Claude Desktop.
5. Ask Claude: “What Apify Actors can I use?”

Integrating with UBOS: A Powerful Synergy

UBOS provides a comprehensive platform for building, deploying, and managing AI Agents. Integrating Apify’s MCP Server with UBOS unlocks even greater potential. UBOS handles the complexities of agent orchestration, data connectivity, and model management, allowing you to focus on building intelligent and impactful AI solutions.

Benefits of Using UBOS with Apify’s MCP Server:

• Simplified Agent Orchestration: UBOS streamlines the process of managing and coordinating multiple AI Agents, allowing you to create sophisticated multi-agent systems that leverage the power of Apify Actors.
• Seamless Data Integration: UBOS enables you to connect your AI Agents to your enterprise data sources, providing them with the context and information they need to make informed decisions.
• Custom AI Agent Development: UBOS empowers you to build custom AI Agents with your own LLM models, tailoring them to your specific business needs and integrating them seamlessly with Apify Actors via the MCP Server.
• Centralized Management and Monitoring: UBOS provides a centralized dashboard for managing and monitoring your AI Agents, giving you complete visibility into their performance and usage.

Actors as Tools

Any Apify Actor can be used as a tool. The server is pre-configured with some Actors, but this can be overridden by providing Actor input. Some of the default actors are:

text ‘apify/instagram-scraper’ ‘apify/rag-web-browser’ ‘lukaskrivka/google-maps-with-contact-details’

The tool name must always be the full Actor name, such as apify/rag-web-browser. The arguments for an MCP tool represent the input parameters of the Actor. For example, for the apify/rag-web-browser Actor, the arguments are:

{ “query”: “restaurants in San Francisco”, “maxResults”: 3 }

Helper Tools

The server provides a set of helper tools to discover available Actors and retrieve their details:

• get-actor-details: Retrieves documentation, input schema, and details about a specific Actor.
• discover-actors: Searches for relevant Actors using keywords and returns their details.

There are also tools to manage the available tools list. However, dynamically adding and removing tools requires the MCP client to have the capability to update the tools list, which is typically not supported.

Conclusion

Apify’s MCP Server, combined with the power of UBOS, offers a compelling solution for businesses looking to unlock the full potential of AI Agents. By seamlessly connecting AI models to real-world data and tools, this integration empowers organizations to automate complex workflows, gain valuable insights, and drive innovation. Embrace the future of AI with UBOS and Apify’s MCP Server.

Ready to revolutionize your AI strategy? Contact us today to learn how UBOS can help you harness the power of AI Agents and transform your business.