Enhanced AutoGen MCP Server
A comprehensive MCP server that provides deep integration with Microsoft's AutoGen framework v0.9+, featuring the latest capabilities including prompts, resources, advanced workflows, and enhanced agent types. This server enables sophisticated multi-agent conversations through a standardized Model Context Protocol interface.
🚀 Latest Features (v0.2.0)
✨ Enhanced MCP Support
- Prompts: Pre-built templates for common workflows (code review, research, creative writing)
- Resources: Real-time access to agent status, chat history, and configurations
- Dynamic Content: Template-based prompts with arguments and embedded resources
- Latest MCP SDK: Version 1.12.3 with full feature support
🤖 Advanced Agent Types
- Assistant Agents: Enhanced with latest LLM capabilities
- Conversable Agents: Flexible conversation patterns
- Teachable Agents: Learning and memory persistence
- Retrievable Agents: Knowledge base integration
- Multimodal Agents: Image and document processing (when available)
🔄 Sophisticated Workflows
- Code Generation: Architect → Developer → Reviewer → Executor pipeline
- Research Analysis: Researcher → Analyst → Critic → Synthesizer workflow
- Creative Writing: Multi-stage creative collaboration
- Problem Solving: Structured approach to complex problems
- Code Review: Security → Performance → Style review teams
- Custom Workflows: Build your own agent collaboration patterns
🎯 Enhanced Chat Capabilities
- Smart Speaker Selection: Auto, manual, random, round-robin modes
- Nested Conversations: Hierarchical agent interactions
- Swarm Intelligence: Coordinated multi-agent problem solving
- Memory Management: Persistent agent knowledge and preferences
- Quality Checks: Built-in validation and improvement loops
🛠️ Available Tools
Core Agent Management
create_agent
- Create agents with advanced configurationscreate_workflow
- Build complete multi-agent workflowsget_agent_status
- Detailed agent metrics and health monitoring
Conversation Execution
execute_chat
- Enhanced two-agent conversationsexecute_group_chat
- Multi-agent group discussionsexecute_nested_chat
- Hierarchical conversation structuresexecute_swarm
- Swarm-based collaborative problem solving
Workflow Orchestration
execute_workflow
- Run predefined workflow templatesmanage_agent_memory
- Handle agent learning and persistenceconfigure_teachability
- Enable/configure agent learning capabilities
📝 Available Prompts
autogen-workflow
Create sophisticated multi-agent workflows with customizable parameters:
- Arguments:
task_description
,agent_count
,workflow_type
- Use case: Rapid workflow prototyping and deployment
code-review
Set up collaborative code review with specialized agents:
- Arguments:
code
,language
,focus_areas
- Use case: Comprehensive code quality assessment
research-analysis
Deploy research teams for in-depth topic analysis:
- Arguments:
topic
,depth
- Use case: Academic research, market analysis, technical investigation
📊 Available Resources
autogen://agents/list
Live list of active agents with status and capabilities
autogen://workflows/templates
Available workflow templates and configurations
autogen://chat/history
Recent conversation history and interaction logs
autogen://config/current
Current server configuration and settings
Installation
Installing via Smithery
To install AutoGen Server for Claude Desktop automatically via Smithery:
Manual Installation
- Clone the repository:
- Install Node.js dependencies:
- Install Python dependencies:
- Build the TypeScript project:
- Set up configuration:
Configuration
Environment Variables
Create a .env
file from the template:
Configuration File
Update config.json
with your preferences:
Usage Examples
Using with Claude Desktop
Add to your claude_desktop_config.json
:
Command Line Testing
Test the server functionality:
Using Prompts
The server provides several built-in prompts:
- autogen-workflow - Create multi-agent workflows
- code-review - Set up collaborative code review
- research-analysis - Deploy research teams
Accessing Resources
Available resources provide real-time data:
autogen://agents/list
- Current active agentsautogen://workflows/templates
- Available workflow templatesautogen://chat/history
- Recent conversation historyautogen://config/current
- Server configuration
Workflow Examples
Code Generation Workflow
Research Workflow
Advanced Features
Agent Types
- Assistant Agents: LLM-powered conversational agents
- User Proxy Agents: Code execution and human interaction
- Conversable Agents: Flexible conversation patterns
- Teachable Agents: Learning and memory persistence (when available)
- Retrievable Agents: Knowledge base integration (when available)
Chat Modes
- Two-Agent Chat: Direct conversation between agents
- Group Chat: Multi-agent discussions with smart speaker selection
- Nested Chat: Hierarchical conversation structures
- Swarm Intelligence: Coordinated problem solving (experimental)
Memory Management
- Persistent agent memory across sessions
- Conversation history tracking
- Learning from interactions (teachable agents)
- Memory cleanup and optimization
Troubleshooting
Common Issues
- API Key Errors: Ensure your OpenAI API key is valid and has sufficient credits
- Import Errors: Install all dependencies with
pip install -r requirements.txt --user
- Build Failures: Check Node.js version (>= 18) and run
npm install
- Chat Failures: Verify agent creation succeeded before attempting conversations
Debug Mode
Enable detailed logging:
Performance Tips
- Use
gpt-4o-mini
for faster, cost-effective operations - Enable caching for repeated operations
- Set appropriate timeout values for long-running workflows
- Use quality checks only when needed (increases execution time)
Development
Running Tests
Building
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Submit a pull request
Version History
v0.2.0 (Latest)
- ✨ Enhanced MCP support with prompts and resources
- 🤖 Advanced agent types (teachable, retrievable)
- 🔄 Sophisticated workflows with quality checks
- 🎯 Smart speaker selection and nested conversations
- 📊 Real-time resource monitoring
- 🧠 Memory management and persistence
v0.1.0
- Basic AutoGen integration
- Simple agent creation and chat execution
- MCP tool interface
Support
For issues and questions:
- Check the troubleshooting section above
- Review the test examples in
test_server.py
- Open an issue on GitHub with detailed reproduction steps
License
MIT License - see LICENSE file for details.
OpenAI API Key (optional, can also be set in config.json)
OPENAI_API_KEY=your-openai-api-key
- Configure the server settings:
Available Operations
The server supports three main operations:
1. Creating Agents
2. One-on-One Chat
3. Group Chat
Error Handling
Common error scenarios include:
- Agent Creation Errors
- Execution Errors
- Configuration Errors
Architecture
The server follows a modular architecture:
License
MIT License - See LICENSE file for details
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Microsoft の AutoGen フレームワークとの統合を提供し、標準化されたインターフェースを通じてマルチエージェント会話を可能にする MCP サーバー。
Related MCP Servers
- -securityFlicense-qualityAn MCP (Multi-Agent Conversation Protocol) server that enables interaction with Google's Managed Service for Microsoft Active Directory through its OpenAPI, allowing users to manage identity resources through natural language.Last updated -
- -securityFlicense-qualityAn MCP Server that enables multi-agent conversation interactions with the Stellastra API, auto-generated using AG2's MCP builder.Last updated -
- -securityFlicense-qualityAn auto-generated MCP server that enables interaction with the OpenAI API, allowing users to access OpenAI's models and capabilities through the Multi-Agent Conversation Protocol.Last updated -
- AsecurityFlicenseAqualityAn intelligent MCP server that orchestrates multiple MCP servers with AI-enhanced workflow automation and production-ready context engine capabilities for codebase analysis.Last updated -3