On your computer
- MCPtoAI Desktop and the Device Agent
- Your AI provider API keys
- Local models (Ollama, LM Studio)
- Your files, applications and permission settings
How it works
From installation to your first task.
MCPtoAI has three parts: the web workspace, a secure relay and the Device Agent on your computer. Here is how they work together.
Set up in five steps.
No Terminal or configuration files — everything happens in the app and the browser.
- 1
Install MCPtoAI Desktop
Download the app for macOS, move it to Applications and open it.
- 2
Install the Device Agent
From inside the app, install the bundled Device Agent. It runs quietly in the background and starts with your computer.
- 3
Connect your account
Sign in through your browser to pair the device with your MCPtoAI account. A unique cryptographic identity is created for the device.
- 4
Add an AI provider
Enter an API key for a cloud provider, or use a local model. Keys are saved in your operating system's credential store.
- 5
Work from anywhere
Open MCPtoAI Web on any computer or phone, choose your device and a model, and start a conversation.
What happens when you send a message.
- 1
You send a message
from MCPtoAI Web or MCPtoAI Desktop.
- 2
The relay delivers it
over an encrypted connection to your paired device.
- 3
Your device calls the AI
with your own provider key, stored on the device.
- 4
Tools run under your rules
Off, Ask or Allow decides what may happen.
- 5
You get the result
in the same conversation, on any device.
What runs where.
MCPtoAI keeps the sensitive parts on your computer and uses the cloud only where it is needed.
In the MCPtoAI cloud
- MCPtoAI Web
- The secure relay
- Your account and paired devices
- Conversation history, so you can continue anywhere
With services you choose
- The AI providers you add
- The MCP services you connect
- Each under your own account and terms
You decide what AI may do.
Every capability of your computer and every MCP tool has one of three levels.
The AI cannot use this capability or tool.
The AI asks first. Nothing happens until you approve it in the conversation.
The AI may use it without asking — useful for low-risk actions such as listing files.
Some actions always ask
Writing files, opening applications or links, capturing the screen, camera or microphone, and running commands always require your approval, whatever the setting. Running commands is turned off by default.
Ready to try it?
Download MCPtoAI Desktop and connect your first device in a few minutes.