MCP Catalogs
← Homemcp_autogen_sse_stdio screenshot

mcp_autogen_sse_stdio

by SaM-92·★ 29·Score 38

A practical example demonstrating AutoGen integration with both local and remote MCP servers using Stdio and SSE.

developer-toolsai-llmother
7
Forks
1
Open issues
13 mo ago
Last commit
2d ago
Indexed

Overview

This repository provides a clear demonstration of how to integrate MCP servers with AutoGen, showing both local and remote tool connections. The implementation includes a local math server using Stdio transport and a remote Apify tool via SSE for web browsing capabilities. The README is well-structured with detailed setup instructions and code walkthroughs.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Building AI agents with multiple tool integrations
you:Implementing local math tools for computational tasks
you:Adding web browsing capabilities to AI agents via remote MCP servers
you:What is the purpose of this MCP server?
you:Can I use other MCP servers with this approach?

When to choose this

Choose this when you need to integrate AutoGen with both local and remote MCP tools, particularly when working with hybrid architectures combining simple calculation tools with external web services.

When NOT to choose this

Not suitable for production environments requiring extensive tool integration as this is a demonstration project focused on showing protocol capabilities rather than providing a comprehensive solution.

Tools this server exposes

4 tools extracted from the README
  • add

    Performs addition of two numbers

  • multiply

    Performs multiplication of two numbers

  • web_search

    Searches the web for information

  • content_retrieval

    Retrieves and analyzes content from web pages

Note: Tools are explicitly described in the README: local math tools (add, multiply) and remote web browsing tools (web_search, content_retrieval) from Apify

Comparable tools

auto-gen-mcpmcp-server-examplesagi-mcp

Installation

Installation

  1. Ensure you have **Python 3.12** installed
  2. Install uv: pip install uv
  3. Create virtual environment: uv venv --python 3.12
  4. Activate virtual environment:

- macOS/Linux: source .venv/bin/activate - Windows: \.venv\Scripts\activate

  1. Install dependencies: uv pip install -e .
  2. Create .env file with your API keys:

``dotenv OPENAI_API_KEY=your_openai_api_key_here APIFY_API_KEY=your_apify_api_key_here ``

  1. Run with: uv run mcp_autogen_sse_stdio/main.py

FAQ

What is the purpose of this MCP server?
This is not an MCP server itself but rather an example of how to integrate both local and remote MCP servers into AutoGen agents.
Can I use other MCP servers with this approach?
Yes, the example demonstrates the pattern for connecting any MCP servers via Stdio or SSE transport, not just the math server and Apify tool shown.

Compare mcp_autogen_sse_stdio with

mcp_autogen_sse_stdio vs ultimate_mcp_servermcp_autogen_sse_stdio vs mcp-server-chartmcp_autogen_sse_stdio vs everythingmcp_autogen_sse_stdio vs filesystemmcp_autogen_sse_stdio vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.