Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
161f87b37b | ||
|
|
c38ce033fa |
@@ -1,199 +0,0 @@
|
|||||||
# Copilot Instructions for Autogen-MCP-Server
|
|
||||||
|
|
||||||
## Project Overview
|
|
||||||
This project implements a hierarchical MCP (Model Context Protocol) server system using AutoGen multi-agent architecture. The system acts as a coordinator for multiple specialized MCP servers through configurable AI agents.
|
|
||||||
|
|
||||||
## Architecture
|
|
||||||
- **Main MCP Server**: Entry point for MCP-capable clients (e.g., AnythingLLM)
|
|
||||||
- **AutoGen Framework**: Multi-agent coordination system
|
|
||||||
- **Moderator Agent**: Orchestrates and routes requests to specialized agents
|
|
||||||
- **Specialized Agents**: Each agent handles specific domains (Azure DevOps, Database, etc.)
|
|
||||||
- **MCP Server Integration**: Each specialized agent connects to dedicated MCP servers
|
|
||||||
- **Configuration-Driven**: YAML/JSON configuration for agent setup and routing
|
|
||||||
- **FastMCP**: The main MCP server implementation MUST use FastMCP as the protocol and server library. No other MCP server implementation is allowed for the entry point.
|
|
||||||
|
|
||||||
## Key Components
|
|
||||||
|
|
||||||
### 1. MCP Server (Entry Point)
|
|
||||||
- Implements MCP protocol using **FastMCP** (mandatory)
|
|
||||||
- Receives requests from clients
|
|
||||||
- Forwards to AutoGen moderator
|
|
||||||
- Returns responses back to clients
|
|
||||||
|
|
||||||
### 2. Moderator Agent
|
|
||||||
- Analyzes incoming requests
|
|
||||||
- Determines appropriate specialized agent
|
|
||||||
- Coordinates multi-agent conversations
|
|
||||||
- Aggregates and formats responses
|
|
||||||
|
|
||||||
### 3. Specialized Agents
|
|
||||||
- Domain-specific expertise
|
|
||||||
- Connected to specialized MCP servers
|
|
||||||
- Configurable via YAML/JSON
|
|
||||||
- Pluggable architecture
|
|
||||||
|
|
||||||
### 4. Configuration System
|
|
||||||
- Agent definitions in YAML/JSON
|
|
||||||
- Routing rules based on keywords/patterns
|
|
||||||
- MCP server connections
|
|
||||||
- Model configurations
|
|
||||||
- Fallback strategies
|
|
||||||
|
|
||||||
## Development Guidelines
|
|
||||||
|
|
||||||
### Virtual Environment Management
|
|
||||||
- **ALWAYS activate the .venv before running any terminal commands**
|
|
||||||
- Use `source .venv/bin/activate` (Linux/macOS) or `.venv\Scripts\activate` (Windows)
|
|
||||||
- Never run Python commands or install packages without the virtual environment activated
|
|
||||||
- All pip installs, python executions, and package management must be done within the .venv
|
|
||||||
|
|
||||||
### Project Cleanliness
|
|
||||||
- **Keep the project structure clean and organized**
|
|
||||||
- After creating new files, verify they are actually needed and remove unnecessary ones
|
|
||||||
- Do not create duplicate files in subdirectories
|
|
||||||
- **NEVER create copies of existing files in subdirectories**
|
|
||||||
- Before creating a new file, check if a similar file already exists
|
|
||||||
- Remove temporary files, unused imports, and dead code regularly
|
|
||||||
- Maintain a minimal and focused project structure
|
|
||||||
|
|
||||||
### File Management Rules
|
|
||||||
- **Check for existing files before creating new ones**
|
|
||||||
- Use existing files and extend them rather than creating duplicates
|
|
||||||
- If a file needs to be moved, use proper refactoring instead of copying
|
|
||||||
- Remove any files that become obsolete after refactoring
|
|
||||||
- Keep related functionality in the same file when appropriate
|
|
||||||
|
|
||||||
### Code Structure
|
|
||||||
```
|
|
||||||
├── src/ # Source code
|
|
||||||
│ ├── mcp_server/ # Main MCP server implementation
|
|
||||||
│ ├── agents/ # AutoGen agent implementations
|
|
||||||
│ │ ├── moderator.py # Moderator agent
|
|
||||||
│ │ ├── base_agent.py # Base class for specialized agents
|
|
||||||
│ │ └── specialized/ # Specialized agent implementations
|
|
||||||
│ ├── config/ # Configuration management
|
|
||||||
│ ├── utils/ # Utility functions
|
|
||||||
│ ├── web_ui/ # Web UI for configuration management
|
|
||||||
│ │ ├── api/ # REST API endpoints
|
|
||||||
│ │ ├── static/ # CSS, JS, images
|
|
||||||
│ │ └── templates/ # HTML templates
|
|
||||||
│ └── main.py # Entry point
|
|
||||||
├── config/ # Configuration files
|
|
||||||
│ ├── example-config.yml # Example configuration
|
|
||||||
│ └── config.yml # Actual configuration (not in git)
|
|
||||||
├── tests/ # Test files
|
|
||||||
│ ├── unit/ # Unit tests
|
|
||||||
│ └── integration/ # Integration tests
|
|
||||||
├── logs/ # Log files (not in git)
|
|
||||||
├── docs/ # Documentation
|
|
||||||
├── requirements.txt # Python dependencies
|
|
||||||
├── requirements-dev.txt # Development dependencies
|
|
||||||
└── .venv/ # Virtual environment
|
|
||||||
```
|
|
||||||
|
|
||||||
### Configuration Format
|
|
||||||
```yaml
|
|
||||||
moderator:
|
|
||||||
name: "AgentModerator"
|
|
||||||
model: "gpt-4"
|
|
||||||
system_message: "..."
|
|
||||||
|
|
||||||
agents:
|
|
||||||
- name: "AzureDevOpsAgent"
|
|
||||||
specialization: "azure_devops"
|
|
||||||
model: "gpt-4"
|
|
||||||
mcp_server:
|
|
||||||
url: "mcp://azure-devops-server"
|
|
||||||
tools: ["get_work_items", "create_pull_request"]
|
|
||||||
|
|
||||||
routing_rules:
|
|
||||||
- keywords: ["azure", "devops", "pipeline"]
|
|
||||||
agent: "AzureDevOpsAgent"
|
|
||||||
```
|
|
||||||
|
|
||||||
### Key Technologies
|
|
||||||
- **Python 3.12+** (3.13+ preferred when available)
|
|
||||||
- **FastMCP**: Mandatory for the main MCP server implementation
|
|
||||||
- **AutoGen**: Multi-agent framework
|
|
||||||
- **MCP SDK**: Model Context Protocol implementation
|
|
||||||
- **FastAPI**: Modern web framework for Web UI
|
|
||||||
- **Pydantic**: Configuration validation
|
|
||||||
- **PyYAML**: Configuration parsing
|
|
||||||
- **AsyncIO**: Asynchronous operations
|
|
||||||
- **SQLAlchemy**: Database ORM (for configuration storage)
|
|
||||||
- **Uvicorn**: ASGI server
|
|
||||||
|
|
||||||
### Development Phases
|
|
||||||
1. **Phase 1**: Basic MCP server + single specialized agent
|
|
||||||
2. **Phase 2**: Moderator agent + routing logic
|
|
||||||
3. **Phase 3**: Configuration system + multiple agents
|
|
||||||
4. **Phase 4**: Error handling + monitoring
|
|
||||||
5. **Phase 5**: Plugin system + hot-reload
|
|
||||||
|
|
||||||
### Testing Strategy
|
|
||||||
- Unit tests for each component
|
|
||||||
- Integration tests for agent communication
|
|
||||||
- Configuration validation tests
|
|
||||||
- End-to-end tests with real MCP clients
|
|
||||||
- Performance tests for multi-agent scenarios
|
|
||||||
|
|
||||||
### Error Handling
|
|
||||||
- Graceful degradation when agents/servers unavailable
|
|
||||||
- Timeout handling for long-running operations
|
|
||||||
- Fallback strategies in configuration
|
|
||||||
- Comprehensive logging and monitoring
|
|
||||||
|
|
||||||
### Performance Considerations
|
|
||||||
- Async/await for non-blocking operations
|
|
||||||
- Connection pooling for MCP servers
|
|
||||||
- Request caching where appropriate
|
|
||||||
- Token usage optimization
|
|
||||||
|
|
||||||
## Implementation Notes
|
|
||||||
|
|
||||||
### Agent Factory Pattern
|
|
||||||
Use factory pattern to create agents from configuration:
|
|
||||||
```python
|
|
||||||
class AgentFactory:
|
|
||||||
@staticmethod
|
|
||||||
def create_agent(config: AgentConfig) -> BaseAgent:
|
|
||||||
# Create agent based on configuration
|
|
||||||
```
|
|
||||||
|
|
||||||
### MCP Server Registry
|
|
||||||
Maintain registry of available MCP servers:
|
|
||||||
```python
|
|
||||||
class MCPServerRegistry:
|
|
||||||
def register_server(self, name: str, server: MCPServer):
|
|
||||||
# Register MCP server
|
|
||||||
|
|
||||||
def get_server(self, name: str) -> MCPServer:
|
|
||||||
# Get MCP server by name
|
|
||||||
```
|
|
||||||
|
|
||||||
### Configuration Hot-Reload
|
|
||||||
Implement configuration reload without restart:
|
|
||||||
```python
|
|
||||||
class ConfigManager:
|
|
||||||
def reload_config(self):
|
|
||||||
# Reload configuration and update agents
|
|
||||||
```
|
|
||||||
|
|
||||||
## Security Considerations
|
|
||||||
- Validate all configuration inputs
|
|
||||||
- Sanitize requests between agents
|
|
||||||
- Implement proper authentication for MCP servers
|
|
||||||
- Log all agent interactions for audit
|
|
||||||
|
|
||||||
## Monitoring & Observability
|
|
||||||
- Request tracing across agent boundaries
|
|
||||||
- Performance metrics collection
|
|
||||||
- Error rate monitoring
|
|
||||||
- Token usage tracking
|
|
||||||
|
|
||||||
## Future Enhancements
|
|
||||||
- Web UI for configuration management
|
|
||||||
- Agent performance analytics
|
|
||||||
- Dynamic agent scaling
|
|
||||||
- Advanced routing algorithms
|
|
||||||
- Integration with more MCP servers
|
|
||||||
34
CHANGELOG.md
Normal file
34
CHANGELOG.md
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
# Changelog
|
||||||
|
|
||||||
|
Alle bemerkenswerten Änderungen an diesem Projekt werden in dieser Datei dokumentiert.
|
||||||
|
|
||||||
|
Das Format basiert auf [Keep a Changelog](https://keepachangelog.com/de/1.0.0/),
|
||||||
|
und dieses Projekt folgt [Semantic Versioning](https://semver.org/lang/de/).
|
||||||
|
|
||||||
|
## [Unreleased]
|
||||||
|
|
||||||
|
### Added
|
||||||
|
-
|
||||||
|
|
||||||
|
### Changed
|
||||||
|
-
|
||||||
|
|
||||||
|
### Deprecated
|
||||||
|
-
|
||||||
|
|
||||||
|
### Removed
|
||||||
|
-
|
||||||
|
|
||||||
|
### Fixed
|
||||||
|
-
|
||||||
|
|
||||||
|
### Security
|
||||||
|
-
|
||||||
|
|
||||||
|
## [1.0.0] - 2026-04-12
|
||||||
|
|
||||||
|
### Added
|
||||||
|
- Initiale Version
|
||||||
|
|
||||||
|
[Unreleased]: https://github.com/Konnos/Autogen-MCP-Server/compare/v1.0.0...HEAD
|
||||||
|
[1.0.0]: https://github.com/Konnos/Autogen-MCP-Server/releases/tag/v1.0.0
|
||||||
46
CONTRIBUTING.md
Normal file
46
CONTRIBUTING.md
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
# Contribution Guidelines
|
||||||
|
|
||||||
|
Vielen Dank dafür, dass Sie zu diesem Projekt beitragen möchten!
|
||||||
|
|
||||||
|
## Wie kann ich beitragen?
|
||||||
|
|
||||||
|
### Bugs berichten
|
||||||
|
- Erstellen Sie ein Issue mit dem Label "bug"
|
||||||
|
- Beschreiben Sie das Problem so detailliert wie möglich
|
||||||
|
- Geben Sie Schritte zur Reproduktion an
|
||||||
|
- Teilen Sie Ihre Umgebung mit (OS, Software-Version, etc.)
|
||||||
|
|
||||||
|
### Features vorschlagen
|
||||||
|
- Erstellen Sie ein Issue mit dem Label "enhancement"
|
||||||
|
- Beschreiben Sie das Feature und seinen Nutzen
|
||||||
|
- Geben Sie Beispiele für die Verwendung an
|
||||||
|
|
||||||
|
### Code beitragen
|
||||||
|
1. **Fork** dieses Repository
|
||||||
|
2. **Clone** Ihren Fork: `git clone <your-fork-url>`
|
||||||
|
3. **Branch erstellen**: `git checkout -b feature/your-feature`
|
||||||
|
4. **Änderungen committen**: `git commit -m 'Add some feature'`
|
||||||
|
5. **Push**: `git push origin feature/your-feature`
|
||||||
|
6. **Pull Request** erstellen
|
||||||
|
|
||||||
|
## Code-Stil
|
||||||
|
|
||||||
|
- Folgen Sie den bestehenden Code-Konventionen
|
||||||
|
- Schreiben Sie aussagekräftige Commit-Messages
|
||||||
|
- Dokumentieren Sie Ihre Änderungen
|
||||||
|
|
||||||
|
## Pull Request Prozess
|
||||||
|
|
||||||
|
1. Update die Dokumentation wenn nötig
|
||||||
|
2. Sorgen Sie dafür, dass Tests bestehen (sofern vorhanden)
|
||||||
|
3. Erstellen Sie einen PR mit klarer Beschreibung
|
||||||
|
4. Warten Sie auf Review
|
||||||
|
|
||||||
|
## Lizenz
|
||||||
|
|
||||||
|
Durch das Einreichen von Beiträgen erklären Sie sich damit einverstanden, dass diese unter derselben Lizenz wie das Projekt lizenziert sind.
|
||||||
|
|
||||||
|
## Fragen?
|
||||||
|
|
||||||
|
Erstellen Sie ein Issue oder kontaktieren Sie die Maintainer.
|
||||||
|
|
||||||
187
README.md
187
README.md
@@ -1,184 +1,35 @@
|
|||||||
# Autogen-MCP-Server
|
# Autogen-MCP-Server
|
||||||
|
|
||||||
Ein hierarchisches MCP-System mit AutoGen Multi-Agent-Architektur für die Koordination spezialisierter KI-Agenten.
|
Ein MCP Server, der eine Gruppe von LLM und MCP Servern koppelt für verteilte Agenten-Kommunikation.
|
||||||
|
|
||||||
## 🎯 Projektziel
|
## Übersicht
|
||||||
|
|
||||||
Dieses Projekt implementiert einen intelligenten MCP (Model Context Protocol) Server, der als Einstiegspunkt für ein System aus spezialisierten KI-Agenten fungiert. Das System ermöglicht es, komplexe Anfragen automatisch an die am besten geeigneten Experten-Agenten zu routen und koordinierte Antworten zu liefern.
|
Dieser Server implementiert das Model Context Protocol (MCP) und ermöglicht:
|
||||||
|
- Kommunikation zwischen mehreren LLM-Modellen
|
||||||
|
- Verteilte Agent-Architektur
|
||||||
|
- Autogen Integration
|
||||||
|
|
||||||
## 🏗️ Architektur
|
## Features
|
||||||
|
|
||||||
```
|
- Multi-LLM Support
|
||||||
MCP Client (AnythingLLM)
|
- MCP Protocol Implementierung
|
||||||
↓
|
- Agent-Koordination
|
||||||
Hauptserver (MCP Server)
|
- Serverbasierte Infrastruktur
|
||||||
↓
|
|
||||||
Moderator-Agent (AutoGen)
|
|
||||||
↓
|
|
||||||
Spezialisierte Agenten
|
|
||||||
↓
|
|
||||||
Spezialisierte MCP Server
|
|
||||||
```
|
|
||||||
|
|
||||||
### Komponenten
|
## Installation
|
||||||
|
|
||||||
- **🚪 Hauptserver**: MCP-konformer Einstiegspunkt für Clients
|
|
||||||
- **🎭 Moderator-Agent**: Intelligente Koordination und Routing
|
|
||||||
- **🔧 Spezialisierte Agenten**: Experten für spezifische Domänen (Azure DevOps, Datenbanken, etc.)
|
|
||||||
- **⚙️ MCP-Server**: Spezialisierte Backend-Services für jeden Agenten
|
|
||||||
- **📋 Konfigurationssystem**: YAML/JSON-basierte Agenten-Konfiguration
|
|
||||||
|
|
||||||
## 🌟 Hauptfeatures
|
|
||||||
|
|
||||||
### ✅ Intelligente Anfragerouting
|
|
||||||
- Automatische Erkennung der passenden Experten-Agenten
|
|
||||||
- Keyword-basierte und semantische Routing-Regeln
|
|
||||||
- Fallback-Strategien für unbekannte Anfragen
|
|
||||||
|
|
||||||
### ✅ Konfigurierbare Agenten
|
|
||||||
- YAML/JSON-Konfiguration für alle Agenten
|
|
||||||
- Plug-and-Play-Architektur für neue Domänen
|
|
||||||
- Hot-Reload für Konfigurationsänderungen
|
|
||||||
|
|
||||||
### ✅ Enterprise-Ready
|
|
||||||
- Umfassende Fehlerbehandlung
|
|
||||||
- Logging und Monitoring
|
|
||||||
- Skalierbare Architektur
|
|
||||||
- Sicherheitsfeatures
|
|
||||||
|
|
||||||
## 🚀 Anwendungsfall
|
|
||||||
|
|
||||||
**Beispiel-Workflow:**
|
|
||||||
1. Benutzer stellt Frage zu Azure DevOps in AnythingLLM
|
|
||||||
2. AnythingLLM sendet Anfrage an unseren MCP Server
|
|
||||||
3. Moderator-Agent analysiert die Anfrage
|
|
||||||
4. Azure DevOps-Spezialist wird aktiviert
|
|
||||||
5. Spezialist nutzt Azure DevOps MCP Server für Informationen
|
|
||||||
6. Antwort wird über die Kette zurück an den Benutzer geliefert
|
|
||||||
|
|
||||||
## 📝 Konfigurationsbeispiel
|
|
||||||
|
|
||||||
```yaml
|
|
||||||
# autogen-config.yml
|
|
||||||
moderator:
|
|
||||||
name: "AgentModerator"
|
|
||||||
model: "gpt-4"
|
|
||||||
system_message: "Du koordinierst spezialisierte Agenten..."
|
|
||||||
|
|
||||||
agents:
|
|
||||||
- name: "AzureDevOpsAgent"
|
|
||||||
specialization: "azure_devops"
|
|
||||||
model: "gpt-4"
|
|
||||||
mcp_server:
|
|
||||||
url: "mcp://azure-devops-server"
|
|
||||||
tools: ["get_work_items", "create_pull_request"]
|
|
||||||
|
|
||||||
- name: "DatabaseAgent"
|
|
||||||
specialization: "database"
|
|
||||||
model: "gpt-3.5-turbo"
|
|
||||||
mcp_server:
|
|
||||||
url: "mcp://database-server"
|
|
||||||
tools: ["query_db", "get_schema"]
|
|
||||||
|
|
||||||
routing_rules:
|
|
||||||
- keywords: ["azure", "devops", "pipeline", "build"]
|
|
||||||
agent: "AzureDevOpsAgent"
|
|
||||||
- keywords: ["database", "sql", "query", "table"]
|
|
||||||
agent: "DatabaseAgent"
|
|
||||||
```
|
|
||||||
|
|
||||||
## 🛠️ Technologie-Stack
|
|
||||||
|
|
||||||
- **Python 3.13+**
|
|
||||||
- **AutoGen**: Multi-Agent Framework
|
|
||||||
- **MCP SDK**: Model Context Protocol
|
|
||||||
- **Pydantic**: Konfigurationsvalidierung
|
|
||||||
- **PyYAML**: Konfigurationsparsing
|
|
||||||
- **AsyncIO**: Asynchrone Operationen
|
|
||||||
|
|
||||||
## 🎯 Entwicklungsphasen
|
|
||||||
|
|
||||||
### Phase 1: MVP (Minimum Viable Product)
|
|
||||||
- [x] Grundlegende MCP Server Implementierung
|
|
||||||
- [x] Einfacher Spezialist-Agent (Azure DevOps)
|
|
||||||
- [x] Basis-Konfigurationssystem
|
|
||||||
|
|
||||||
### Phase 2: Moderator-System
|
|
||||||
- [ ] Moderator-Agent Implementierung
|
|
||||||
- [ ] Intelligente Anfragerouting
|
|
||||||
- [ ] Multi-Agent-Koordination
|
|
||||||
|
|
||||||
### Phase 3: Erweiterte Konfiguration
|
|
||||||
- [ ] Vollständiges YAML/JSON-Konfigurationssystem
|
|
||||||
- [ ] Mehrere spezialisierte Agenten
|
|
||||||
- [ ] Hot-Reload-Funktionalität
|
|
||||||
|
|
||||||
### Phase 4: Enterprise-Features
|
|
||||||
- [ ] Umfassende Fehlerbehandlung
|
|
||||||
- [ ] Logging und Monitoring
|
|
||||||
- [ ] Performance-Optimierungen
|
|
||||||
|
|
||||||
### Phase 5: Erweiterungen
|
|
||||||
- [ ] Plugin-System für neue Agenten
|
|
||||||
- [ ] Web-UI für Konfiguration
|
|
||||||
- [ ] Analytics und Metriken
|
|
||||||
|
|
||||||
## 🔧 Installation & Setup
|
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# Repository klonen
|
|
||||||
git clone https://github.com/KonnosPB/Autogen-MCP-Server.git
|
|
||||||
cd Autogen-MCP-Server
|
|
||||||
|
|
||||||
# Abhängigkeiten installieren
|
|
||||||
pip install -r requirements.txt
|
pip install -r requirements.txt
|
||||||
|
|
||||||
# Konfiguration anpassen
|
|
||||||
cp config/example-config.yml config/config.yml
|
|
||||||
# config.yml bearbeiten...
|
|
||||||
|
|
||||||
# Server starten
|
|
||||||
python src/main.py
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## 📊 Vorteile
|
## Verwendung
|
||||||
|
|
||||||
### Für Entwickler
|
```bash
|
||||||
- **Modulare Architektur**: Einfache Erweiterung um neue Domänen
|
python server.py
|
||||||
- **Konfigurierbar**: Keine Code-Änderungen für neue Agenten
|
```
|
||||||
- **Testbar**: Isolierte Komponenten für einfache Tests
|
|
||||||
|
|
||||||
### Für Unternehmen
|
Der Server läuft auf dem konfigurierten Port und akzeptiert MCP-Verbindungen.
|
||||||
- **Skalierbar**: Neue Experten-Domänen ohne Neudeployment
|
|
||||||
- **Wartbar**: Zentrale Konfiguration
|
|
||||||
- **Ausfallsicher**: Fallback-Strategien und Fehlerbehandlung
|
|
||||||
|
|
||||||
### Für Benutzer
|
## Konfiguration
|
||||||
- **Intelligent**: Automatische Weiterleitung an die richtige Expertise
|
|
||||||
- **Schnell**: Direkte Verbindung zu spezialisierten Services
|
|
||||||
- **Umfassend**: Ein Interface für viele verschiedene Domänen
|
|
||||||
|
|
||||||
## 🤝 Beitragen
|
Siehe `config.yaml` für Konfigurationsoptionen.
|
||||||
|
|
||||||
Wir freuen uns über Beiträge! Siehe [CONTRIBUTING.md](CONTRIBUTING.md) für Details.
|
|
||||||
|
|
||||||
## 📄 Lizenz
|
|
||||||
|
|
||||||
Dieses Projekt ist unter der MIT-Lizenz lizenziert - siehe [LICENSE](LICENSE) für Details.
|
|
||||||
|
|
||||||
## 🌍 Roadmap
|
|
||||||
|
|
||||||
- **Q1 2025**: MVP mit Azure DevOps Integration
|
|
||||||
- **Q2 2025**: Mehrere spezialisierte Agenten
|
|
||||||
- **Q3 2025**: Enterprise-Features und Monitoring
|
|
||||||
- **Q4 2025**: Plugin-System und Web-UI
|
|
||||||
|
|
||||||
## 📞 Support
|
|
||||||
|
|
||||||
- **Issues**: GitHub Issues für Bugs und Feature-Requests
|
|
||||||
- **Diskussionen**: GitHub Discussions für Fragen und Ideen
|
|
||||||
- **Dokumentation**: [Wiki](https://github.com/KonnosPB/Autogen-MCP-Server/wiki)
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
*Dieses Projekt kombiniert die Kraft von AutoGen Multi-Agent-Systemen mit der Flexibilität des Model Context Protocol für eine neue Generation intelligenter Assistenten.*
|
|
||||||
@@ -1,143 +0,0 @@
|
|||||||
# Beispiel-Konfiguration für Autogen-MCP-Server
|
|
||||||
# Kopiere diese Datei zu config.yml und passe sie an
|
|
||||||
|
|
||||||
# Moderator Agent Konfiguration
|
|
||||||
moderator:
|
|
||||||
name: "AgentModerator"
|
|
||||||
model: "gpt-4"
|
|
||||||
system_message: |
|
|
||||||
Du bist ein intelligenter Moderator-Agent, der Anfragen an spezialisierte Agenten weiterleitet.
|
|
||||||
Analysiere die Anfrage und bestimme den besten Spezialisten für die Aufgabe.
|
|
||||||
Koordiniere die Kommunikation zwischen den Agenten und formatiere die finale Antwort.
|
|
||||||
|
|
||||||
# Modell-spezifische Konfiguration
|
|
||||||
model_config:
|
|
||||||
temperature: 0.7
|
|
||||||
max_tokens: 1000
|
|
||||||
timeout: 30
|
|
||||||
|
|
||||||
# Spezialisierte Agenten
|
|
||||||
agents:
|
|
||||||
- name: "AzureDevOpsAgent"
|
|
||||||
specialization: "azure_devops"
|
|
||||||
description: "Spezialist für Azure DevOps, Build-Pipelines und Deployment"
|
|
||||||
model: "gpt-4"
|
|
||||||
system_message: |
|
|
||||||
Du bist ein Azure DevOps Spezialist. Du hilfst bei:
|
|
||||||
- Work Items und Backlogs
|
|
||||||
- Build und Release Pipelines
|
|
||||||
- Git Repositories und Pull Requests
|
|
||||||
- Deployment Strategien
|
|
||||||
|
|
||||||
# MCP Server Verbindung
|
|
||||||
mcp_server:
|
|
||||||
url: "mcp://localhost:8001/azure-devops"
|
|
||||||
timeout: 60
|
|
||||||
tools:
|
|
||||||
- "get_work_items"
|
|
||||||
- "create_pull_request"
|
|
||||||
- "get_build_status"
|
|
||||||
- "trigger_pipeline"
|
|
||||||
|
|
||||||
model_config:
|
|
||||||
temperature: 0.3
|
|
||||||
max_tokens: 1500
|
|
||||||
|
|
||||||
- name: "DatabaseAgent"
|
|
||||||
specialization: "database"
|
|
||||||
description: "Spezialist für Datenbank-Operationen und SQL"
|
|
||||||
model: "gpt-3.5-turbo"
|
|
||||||
system_message: |
|
|
||||||
Du bist ein Datenbank-Spezialist. Du hilfst bei:
|
|
||||||
- SQL Queries und Optimierung
|
|
||||||
- Datenbank Design und Schema
|
|
||||||
- Performance-Analyse
|
|
||||||
- Backup und Recovery
|
|
||||||
|
|
||||||
mcp_server:
|
|
||||||
url: "mcp://localhost:8002/database"
|
|
||||||
timeout: 45
|
|
||||||
tools:
|
|
||||||
- "query_database"
|
|
||||||
- "get_schema"
|
|
||||||
- "analyze_performance"
|
|
||||||
- "backup_database"
|
|
||||||
|
|
||||||
model_config:
|
|
||||||
temperature: 0.2
|
|
||||||
max_tokens: 1200
|
|
||||||
|
|
||||||
# Routing-Regeln für automatische Agent-Auswahl
|
|
||||||
routing_rules:
|
|
||||||
- keywords: ["azure", "devops", "pipeline", "build", "deployment", "pull request", "work item"]
|
|
||||||
agent: "AzureDevOpsAgent"
|
|
||||||
confidence: 0.8
|
|
||||||
|
|
||||||
- keywords: ["database", "sql", "query", "schema", "table", "performance", "backup"]
|
|
||||||
agent: "DatabaseAgent"
|
|
||||||
confidence: 0.8
|
|
||||||
|
|
||||||
- keywords: ["datenbank", "abfrage", "tabelle", "schema"]
|
|
||||||
agent: "DatabaseAgent"
|
|
||||||
confidence: 0.7
|
|
||||||
|
|
||||||
# Fallback-Strategien
|
|
||||||
fallback:
|
|
||||||
default_agent: "moderator" # Wenn kein spezieller Agent gefunden wird
|
|
||||||
timeout_seconds: 120
|
|
||||||
retry_attempts: 3
|
|
||||||
|
|
||||||
# Wenn ein Agent nicht verfügbar ist
|
|
||||||
unavailable_strategy: "fallback_to_moderator"
|
|
||||||
|
|
||||||
# Fehlerbehandlung
|
|
||||||
error_responses:
|
|
||||||
agent_timeout: "Entschuldigung, der angefragte Service ist momentan nicht verfügbar."
|
|
||||||
mcp_server_error: "Es gab einen Fehler beim Zugriff auf die Backend-Services."
|
|
||||||
general_error: "Ein unerwarteter Fehler ist aufgetreten. Bitte versuchen Sie es später erneut."
|
|
||||||
|
|
||||||
# Logging-Konfiguration
|
|
||||||
logging:
|
|
||||||
level: "INFO"
|
|
||||||
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
|
||||||
file: "logs/autogen-mcp-server.log"
|
|
||||||
max_file_size: "10MB"
|
|
||||||
backup_count: 5
|
|
||||||
|
|
||||||
# Spezielle Logger
|
|
||||||
loggers:
|
|
||||||
agents: "DEBUG"
|
|
||||||
mcp_server: "INFO"
|
|
||||||
config: "WARNING"
|
|
||||||
|
|
||||||
# Web UI Konfiguration (optional)
|
|
||||||
web_ui:
|
|
||||||
enabled: true
|
|
||||||
host: "localhost"
|
|
||||||
port: 8000
|
|
||||||
debug: false
|
|
||||||
|
|
||||||
# Sicherheit
|
|
||||||
secret_key: "your-secret-key-here" # Ändern Sie dies in Produktion!
|
|
||||||
|
|
||||||
# Authentifizierung (optional)
|
|
||||||
auth:
|
|
||||||
enabled: false
|
|
||||||
username: "admin"
|
|
||||||
password: "password" # Ändern Sie dies in Produktion!
|
|
||||||
|
|
||||||
# Performance-Einstellungen
|
|
||||||
performance:
|
|
||||||
# Maximale gleichzeitige Anfragen
|
|
||||||
max_concurrent_requests: 10
|
|
||||||
|
|
||||||
# Caching
|
|
||||||
cache:
|
|
||||||
enabled: true
|
|
||||||
ttl_seconds: 300
|
|
||||||
max_size: 1000
|
|
||||||
|
|
||||||
# Connection Pooling für MCP Server
|
|
||||||
mcp_connection_pool:
|
|
||||||
max_connections: 5
|
|
||||||
timeout: 30
|
|
||||||
@@ -1,27 +0,0 @@
|
|||||||
# Logs Directory
|
|
||||||
|
|
||||||
This directory contains log files for the Autogen-MCP-Server.
|
|
||||||
|
|
||||||
## Log Files
|
|
||||||
|
|
||||||
- `autogen-mcp-server.log` - Main application log
|
|
||||||
- `agents.log` - Agent-specific logs
|
|
||||||
- `mcp-server.log` - MCP server communication logs
|
|
||||||
- `web-ui.log` - Web UI access and error logs
|
|
||||||
|
|
||||||
## Log Rotation
|
|
||||||
|
|
||||||
Log files are automatically rotated when they reach 10MB in size.
|
|
||||||
Up to 5 backup files are kept.
|
|
||||||
|
|
||||||
## Log Levels
|
|
||||||
|
|
||||||
- `DEBUG` - Detailed diagnostic information
|
|
||||||
- `INFO` - General information about system operation
|
|
||||||
- `WARNING` - Warning messages about potential issues
|
|
||||||
- `ERROR` - Error messages about failures
|
|
||||||
- `CRITICAL` - Critical error messages
|
|
||||||
|
|
||||||
## Configuration
|
|
||||||
|
|
||||||
Log configuration can be adjusted in `config/config.yml` under the `logging` section.
|
|
||||||
@@ -1,21 +0,0 @@
|
|||||||
# Development Requirements - zusätzlich zu requirements.txt
|
|
||||||
|
|
||||||
# Code Quality
|
|
||||||
pre-commit>=3.5.0
|
|
||||||
bandit>=1.7.5
|
|
||||||
|
|
||||||
# Testing
|
|
||||||
pytest-xdist>=3.3.0 # Parallel testing
|
|
||||||
pytest-mock>=3.12.0
|
|
||||||
httpx>=0.25.0 # For testing FastAPI endpoints
|
|
||||||
|
|
||||||
# Development Tools
|
|
||||||
ipython>=8.16.0
|
|
||||||
jupyter>=1.0.0
|
|
||||||
|
|
||||||
# Documentation
|
|
||||||
mkdocs-mermaid2-plugin>=1.1.0
|
|
||||||
|
|
||||||
# Type Checking
|
|
||||||
types-PyYAML>=6.0.0
|
|
||||||
types-requests>=2.31.0
|
|
||||||
@@ -1,47 +0,0 @@
|
|||||||
# Requirements for Autogen-MCP-Server
|
|
||||||
|
|
||||||
# Core MCP and AutoGen
|
|
||||||
mcp>=1.0.0
|
|
||||||
autogen-agentchat>=0.2.0
|
|
||||||
|
|
||||||
# Configuration and Validation
|
|
||||||
pydantic>=2.5.0
|
|
||||||
pydantic-settings>=2.1.0
|
|
||||||
PyYAML>=6.0.1
|
|
||||||
|
|
||||||
# Async and Networking
|
|
||||||
aiohttp>=3.9.0
|
|
||||||
asyncio-mqtt>=0.16.0
|
|
||||||
|
|
||||||
# Web UI Framework (FastAPI chosen for modern async support)
|
|
||||||
fastapi>=0.104.0
|
|
||||||
uvicorn[standard]>=0.24.0
|
|
||||||
jinja2>=3.1.0
|
|
||||||
|
|
||||||
# Database (for configuration storage if needed)
|
|
||||||
sqlalchemy>=2.0.0
|
|
||||||
alembic>=1.12.0
|
|
||||||
|
|
||||||
# Logging and Monitoring
|
|
||||||
structlog>=23.2.0
|
|
||||||
prometheus-client>=0.19.0
|
|
||||||
|
|
||||||
# Security
|
|
||||||
python-jose[cryptography]>=3.3.0
|
|
||||||
passlib[bcrypt]>=1.7.4
|
|
||||||
|
|
||||||
# Development and Testing
|
|
||||||
pytest>=7.4.0
|
|
||||||
pytest-asyncio>=0.21.0
|
|
||||||
pytest-cov>=4.1.0
|
|
||||||
black>=23.9.0
|
|
||||||
ruff>=0.1.0
|
|
||||||
mypy>=1.7.0
|
|
||||||
|
|
||||||
# Documentation
|
|
||||||
mkdocs>=1.5.0
|
|
||||||
mkdocs-material>=9.4.0
|
|
||||||
|
|
||||||
# Optional: For advanced features
|
|
||||||
redis>=5.0.0 # For caching and session management
|
|
||||||
celery>=5.3.0 # For background tasks
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Autogen-MCP-Server: A hierarchical MCP system with AutoGen multi-agent architecture.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
AutoGen agents implementation - Moderator and specialized agents.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Specialized agents for different domains (Azure DevOps, Database, etc.).
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Configuration management - YAML/JSON parsing and validation.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
MCP Server implementation - Entry point for MCP-capable clients.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Utility functions - Logging, helpers, and shared functionality.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Web UI for configuration management - Flask/FastAPI based interface.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Web UI API endpoints - REST API for configuration management.
|
|
||||||
"""
|
|
||||||
@@ -1,53 +0,0 @@
|
|||||||
<!DOCTYPE html>
|
|
||||||
<html lang="de">
|
|
||||||
<head>
|
|
||||||
<meta charset="UTF-8">
|
|
||||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
||||||
<title>Autogen-MCP-Server - Konfiguration</title>
|
|
||||||
<style>
|
|
||||||
body {
|
|
||||||
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
|
||||||
margin: 0;
|
|
||||||
padding: 20px;
|
|
||||||
background-color: #f5f5f5;
|
|
||||||
}
|
|
||||||
.container {
|
|
||||||
max-width: 1200px;
|
|
||||||
margin: 0 auto;
|
|
||||||
background: white;
|
|
||||||
padding: 30px;
|
|
||||||
border-radius: 8px;
|
|
||||||
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
|
|
||||||
}
|
|
||||||
h1 {
|
|
||||||
color: #333;
|
|
||||||
text-align: center;
|
|
||||||
margin-bottom: 30px;
|
|
||||||
}
|
|
||||||
.coming-soon {
|
|
||||||
text-align: center;
|
|
||||||
color: #666;
|
|
||||||
font-size: 18px;
|
|
||||||
padding: 40px;
|
|
||||||
}
|
|
||||||
</style>
|
|
||||||
</head>
|
|
||||||
<body>
|
|
||||||
<div class="container">
|
|
||||||
<h1>🚀 Autogen-MCP-Server Web UI</h1>
|
|
||||||
<div class="coming-soon">
|
|
||||||
<h2>🔧 Konfiguration Interface</h2>
|
|
||||||
<p>Die Web-basierte Konfigurationsoberfläche befindet sich in Entwicklung.</p>
|
|
||||||
<p>Features in Planung:</p>
|
|
||||||
<ul style="text-align: left; display: inline-block;">
|
|
||||||
<li>📝 Agent-Konfiguration bearbeiten</li>
|
|
||||||
<li>🔍 Live-Monitoring der Agenten</li>
|
|
||||||
<li>📊 Performance-Metriken</li>
|
|
||||||
<li>🔄 Hot-Reload von Konfigurationen</li>
|
|
||||||
<li>📋 Routing-Regeln verwalten</li>
|
|
||||||
<li>🔐 Sicherheitseinstellungen</li>
|
|
||||||
</ul>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
</body>
|
|
||||||
</html>
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Integration tests for component interactions.
|
|
||||||
"""
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
"""
|
|
||||||
Unit tests for individual components.
|
|
||||||
"""
|
|
||||||
Reference in New Issue
Block a user