Happy slice of mcp pizzaMCP.pizza

mcp_autogen_sse_stdio

MCP.Pizza Chef: SaM-92

The mcp_autogen_sse_stdio client demonstrates how to integrate local and remote MCP servers using the AutoGen framework. It connects a local math tool server via Stdio transport and a remote Apify RAG Web Browser Actor via Server-Sent Events (SSE). This client enables AI agents to perform arithmetic and web browsing tasks by leveraging multiple MCP servers seamlessly.

Unmaintained · No commits in 16 months.

Use This MCP client To

Integrate local math tool server with AI agents via Stdio Connect remote web browsing tool using SSE transport Combine local and remote MCP servers for multi-tool workflows Enable AI agents to perform arithmetic and web search tasks Demonstrate AutoGen framework usage with MCP protocol Build AI assistants that leverage diverse MCP tool servers

README

🤖 MCP Server Examples with AutoGen

This repository provides a practical demonstration of integrating tools with AI agents using the Model Context Protocol (MCP) within the AutoGen framework.

Key Features Demonstrated:

  • Dual MCP Integration: Shows how to connect an AutoGen agent to:
    • A local tool server (math_server.py) using Stdio transport.
    • A remote tool server (Apify's RAG Web Browser Actor) using Server-Sent Events (SSE) transport.
  • Local Tool Example: A simple calculator (add, multiply) running locally via math_server.py.
  • Remote Tool Example: Leveraging Apify's RAG Web Browser Actor via their MCP Server for web searching and content retrieval.
  • AutoGen Agent: An AssistantAgent configured to utilize both sets of tools to answer user queries.

Goal: To illustrate the flexibility of MCP in enabling AI agents to access diverse tools, whether hosted locally or remotely, through standardized communication protocols (Stdio and SSE).

Scenario: The example agent answers two distinct questions:

  1. A math problem ((3 + 5) x 12?), expected to use the local math_server.py.
  2. A request for recent news ("Summarise the latest news of Iran and US negotiations..."), expected to use the remote Apify web browsing tool.

MCP Workflow

📚 Libraries & Frameworks Used

  • AutoGen: AI agent framework (autogen_agentchat, autogen_core, autogen_ext)
  • MCP: Model Context Protocol for tool integration
  • Python-dotenv: For environment variable management
  • OpenAI API: For LLM capabilities
  • Apify API: For web browsing capabilities

🛠️ Setup

Follow these steps carefully to set up your environment:

mcp_autogen_sse_stdio FAQ

How does mcp_autogen_sse_stdio connect to local and remote MCP servers?
It uses Stdio transport for the local math server and Server-Sent Events (SSE) for the remote Apify web browsing server.
What tools are integrated in this MCP client?
A local math tool server for arithmetic and a remote Apify RAG Web Browser Actor for web browsing.
Can this client handle multiple MCP servers simultaneously?
Yes, it demonstrates dual MCP integration enabling AI agents to use both local and remote tools.
What framework does mcp_autogen_sse_stdio use?
It uses the AutoGen framework to orchestrate AI agents and MCP servers.
Is this client suitable for building AI assistants?
Yes, it shows how to build AI assistants that leverage multiple MCP servers for diverse tasks.
Does it support real-time interaction with remote MCP servers?
Yes, it uses SSE transport for real-time communication with remote MCP servers like Apify.
What programming languages or environments are involved?
The local math server is a Python script, and the client integrates with AutoGen, which supports Python-based AI workflows.