🤖 MCP Server Examples with AutoGen

@SaM-92

About 🤖 MCP Server Examples with AutoGen

This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.

#mathgpt #math-solver #math-assistant

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp_autogen_sse_stdio": {
      "command": "uv",
      "args": [
        "venv",
        "--python",
        "3.12"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is 🤖 MCP Server Examples with AutoGen?

This repository demonstrates how to connect AI agents to tools using the Model Context Protocol (MCP) within the AutoGen framework. It shows integration with both a local tool server (Stdio transport) and a remote tool server (SSE transport) to solve real queries.

How to use 🤖 MCP Server Examples with AutoGen?

Set up a Python 3.12 virtual environment with uv, install dependencies via uv pip install -e ., and create a .env file with your OPENAI_API_KEY and APIFY_API_KEY. Run the demo from the parent directory using uv run mcp_autogen_sse_stdio/main.py.

Key features of 🤖 MCP Server Examples with AutoGen

Dual MCP integration: local (Stdio) and remote (SSE) transports
Local calculator tool (add, multiply)
Remote web browsing via Apify’s RAG Web Browser Actor
AutoGen AssistantAgent configured with both tool sets
Standardized communication between AI models and tools

Use cases of 🤖 MCP Server Examples with AutoGen

Solving arithmetic problems using local Python scripts
Summarizing live web news through remote browsing tools
Prototyping multi‑tool AI agents that combine local and cloud resources
Learning how to integrate MCP servers with AutoGen agents

FAQ from 🤖 MCP Server Examples with AutoGen

What MCP transports are demonstrated?

Local tools use StdioServerParams (standard input/output), and remote tools use SseServerParams (Server‑Sent Events).

What runtime requirements are needed?

Python 3.12, the uv package manager, and API keys for OpenAI and Apify.

How do I obtain and configure API keys?

Create a .env file in the mcp_autogen_sse_stdio directory and add OPENAI_API_KEY and APIFY_API_KEY. The Apify key can be obtained from the Apify MCP Server page.

Does this project work with other MCP servers?

The framework generalizes to other MCP servers that support Stdio or SSE transports, though only the Apify remote server is shown.

Is there a visual walkthrough available?

Yes, the repository includes an animated GIF (images/mcp_exmpl.gif) illustrating the workflow.

Frequently asked questions

What MCP transports are demonstrated?

Local tools use StdioServerParams (standard input/output), and remote tools use SseServerParams (Server‑Sent Events).

What runtime requirements are needed?

Python 3.12, the `uv` package manager, and API keys for OpenAI and Apify.

How do I obtain and configure API keys?

Create a `.env` file in the `mcp_autogen_sse_stdio` directory and add `OPENAI_API_KEY` and `APIFY_API_KEY`. The Apify key can be obtained from the Apify MCP Server page.

Does this project work with other MCP servers?

The framework generalizes to other MCP servers that support Stdio or SSE transports, though only the Apify remote server is shown.

Is there a visual walkthrough available?

Yes, the repository includes an animated GIF (`images/mcp_exmpl.gif`) illustrating the workflow.

Comments

Basic information

More Reasoning MCP servers

MCP Sandbox

JohanLi233

Python sandboxes for llms

MCP Advanced Reasoning Server for Cursor AI

AzDeltaQQ

This is a very basic implementation of an Mcp-Reasoning-Server for Cursor AI .

Code Reasoning MCP Server

mettamatt

A code reasoning MCP server, a fork of sequential-thinking

255

🚀 Aider-MCP: AI Coding Server with Universal Auto-Detection

jacv888

Aider-MCP-Upgraded is a production-grade multi-agent AI coding system that combines Desktop Commander (DC) investigation capabilities with Aider's implementation power. Features 70%+ token reduction, modular architecture, and intelligent workflow automation through strategic agen

🐢🚀 Node.js Sandbox MCP Server

alfonsograziano

A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.

154