Introduction

​

Overview

• MCP server lifecycle management and connections
• Agent workflow patterns (parallel, routing, orchestration, etc.)
• Multi-agent coordination
• Integration with multiple LLM providers
• Deployment as MCP servers

​

Key Features

​

MCP Protocol Support

• Connect to any MCP server via stdio, SSE, WebSocket, or HTTP
• Access tools, resources, prompts, and file system roots
• Automatic tool discovery and integration

​

Agent Patterns

• Parallel Processing - Fan-out tasks to multiple agents
• Routing - Intelligent request routing
• Orchestrator-Workers - Plan and execute complex tasks
• Evaluator-Optimizer - Iterative improvement
• Intent Classification - Understand user intent
• Swarm - Multi-agent collaboration
• Deep Orchestrator - Adaptive planning with knowledge extraction

​

Execution Engines

• asyncio - In-memory execution for development and simple deployments
• Temporal - Durable execution with automatic retries, pause/resume, and workflow history

​

LLM Support

• OpenAI (GPT-4, GPT-4o)
• Anthropic (Claude 3, Claude 3.5)
• Google (Gemini)
• Azure OpenAI
• AWS Bedrock
• Local models via Ollama

​

Quick Example

import asyncio
from mcp_agent.app import MCPApp
from mcp_agent.agents.agent import Agent
from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM

app = MCPApp(name="example_agent")

async def main():
    async with app.run() as mcp_agent_app:
        # Create agent with MCP server access
        agent = Agent(
            name="researcher",
            instruction="Research topics using available tools",
            server_names=["fetch", "filesystem"]
        )
        
        async with agent:
            # List available tools from MCP servers
            tools = await agent.list_tools()
            print(f"Available tools: {[t.name for t in tools.tools]}")
            
            # Attach LLM for interaction
            llm = await agent.attach_llm(OpenAIAugmentedLLM)
            
            # Agent can now use MCP server tools
            result = await llm.generate_str("Research quantum computing")
            print(result)

if __name__ == "__main__":
    asyncio.run(main())

​

Example Applications

​

Agent as MCP Server Demo

​

Workflow Orchestration

​

Swarm Intelligence Pattern

• Agent as MCP Server: Deploy agents as MCP servers for Claude Desktop integration (examples/mcp_agent_server)
• Workflow Patterns: All patterns from Anthropic’s Building Effective Agents guide (examples/workflows)
• Basic Agents: Simple agent examples with various MCP servers (examples/basic)
• Temporal Integration: Durable workflow execution examples (examples/temporal)
• Model Providers: Examples for OpenAI, Anthropic, Google, Azure, Bedrock (examples/model_providers)

​

Installation

uv add mcp-agent

pip install mcp-agent

# OpenAI
uv add "mcp-agent[openai]"

# Anthropic
uv add "mcp-agent[anthropic]"

# All providers
uv add "mcp-agent[openai,anthropic,azure,bedrock,google]"

​

Configuration

execution_engine: asyncio  # or temporal
logger:
  transports: [console]
  level: info

mcp:
  servers:
    fetch:
      command: "uvx"
      args: ["mcp-server-fetch"]
    filesystem:
      command: "npx"
      args: ["-y", "@modelcontextprotocol/server-filesystem", "."]

openai:
  default_model: gpt-4o

openai:
  api_key: "sk-..."

​

Project Structure

your-project/
├── agent.py               # Your agent code
├── mcp_agent.config.yaml  # Configuration
├── mcp_agent.secrets.yaml # API keys (gitignored)
└── logs/                  # Execution logs

​

Deployment Options

​

Local Development

​

Production with Temporal

​

As MCP Server

​

MCP Agent Cloud

​

Examples

• Basic agents - Simple patterns and MCP server usage
• Workflow patterns - All patterns from Anthropic’s guide
• Integrations - Claude Desktop, Streamlit, Jupyter
• MCP servers - Agents exposed as MCP servers
• Temporal - Durable execution examples

​

Next Steps

• Installation - Set up your development environment
• Quick Start - Build your first agent
• Core Concepts - Understand agents, workflows, and MCP
• Examples - Learn from working code

​

Resources

• Model Context Protocol - MCP specification
• Building Effective Agents - Anthropic’s guide
• GitHub Repository - Source code
• Discord Community - Get help and discuss