About AI Assistant MCP
AI Assistant MCP is an AI assistant built with FastAPI and Ollama for users who need chat, system monitoring, and control. It brings conversations, resource metrics, file operations, and process management into a web interface.
Key features
- 01Context-aware chat and history management
- 02CPU, memory, disk, and network monitoring
- 03Process tracking and management
- 04File system operations
- 05System health checks and resource alerts
- 06Real-time web interface
Use cases
- 01Review current and historical system metrics
- 02Track processes and manage running tasks
- 03Read or write files through file operation endpoints
- 04Chat with the AI assistant in the web interface
MCP support
Although MCP appears in the project name, the README does not describe MCP tools or resources exposed by the server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAI Assistant MCP
A powerful AI assistant with system monitoring and control capabilities, built with FastAPI and Ollama.
Features
AI Chat Interface
- Interactive chat with AI assistant
- Context-aware conversations
- Support for new chat sessions
- Chat history management
System Monitoring
- Real-time system metrics dashboard
- CPU, memory, disk, and network monitoring
- Process tracking and management
- Resource usage alerts
- Interactive charts and visualizations
System Control
- File system operations
- Process management
- System health checks
- Secure API access
Web Interface
- Modern, responsive design
- Real-time updates
- Easy navigation between features
- User-friendly controls
Setup Instructions
- Clone the repository:
git clone https://github.com/aldindugolli/Arrodes-2.0.git
cd Arrodes-2.0
- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Set up environment variables:
Create a
.envfile with:
SECRET_KEY=your_secret_key_here
- Start the Ollama service:
ollama serve
- Run the application:
python run.py
Usage
Web Interface
Access the web interface at http://localhost:8000:
- Chat with the AI assistant
- Monitor system resources
- Manage files and processes
- View system alerts
API Endpoints
Chat
POST /chat- Send messages to the AI assistantGET /- Access the chat interface
System Monitoring
GET /monitoring- Access the monitoring dashboardGET /monitoring/metrics- Get current system metricsGET /monitoring/history- Get historical metrics dataGET /monitoring/alerts- Get system alerts
System Control
GET /system/files/list/{path}- List directory contentsGET /system/files/read/{path}- Read file contentsPOST /system/files/write- Write to a fileGET /system/processes- List running processesGET /system/processes/{pid}- Get process detailsDELETE /system/processes/{pid}- Terminate a process
Security
- API key authentication for all endpoints
- Secure file system operations
- Process management safety checks
- Environment variable configuration
Development
Project Structure
src/
├── main.py # FastAPI application
├── ollama_client.py # AI integration
├── monitoring.py # System monitoring
├── system_ops.py # System operations
├── security.py # Security utilities
├── config.py # Configuration
└── templates/ # HTML templates
├── index.html # Chat interface
└── monitoring.html # Monitoring dashboard
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
MIT License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.