- PROVISION
- NETWORK
- CONTROL
- HUMAN
Short answer
How can I use my AI to manage cloud infrastructure?
You give your AI client a command, and it uses the Gridscale MCP to execute the request. It handles everything from selecting templates to attaching IP addresses and managing power. You get a fully configured environment without touching a dashboard.
Infrastructure outcomes
What you get
The agent handles the heavy lifting of cloud management.
PROVISION
New instances ready
Your AI selects a template and builds the machine. You get a running instance without manual configuration.
NETWORK
Connected and reachable
The agent maps IP addresses and storage to your new machines. Your network setup happens in the background.
CONTROL
Power management
You can reboot, stop, or start machines through chat. The AI manages the state of your hardware.
HUMAN
Manual oversight
You decide which templates to use and when to trigger power changes. The AI only acts on your direct orders.
The workflow
What your AI does when the request arrives.
The agent translates your text into specific API actions.
Find the right setup
The agent looks through available configurations to find a match for your requirements.
list_templatesBuild the instance
Once a template is chosen, the agent triggers the creation of the virtual machine.
create_serverConfigure connectivity
The agent attaches the necessary IP addresses and storage volumes to the new machine.
link_ip_to_serverlink_storage_to_serverManage state
The agent adjusts the power status of existing machines based on your instructions.
set_server_power
Try it
Copy these to start.
Use these prompts to begin interacting with Gridscale.
Starting points
These are starting points. Swap out the template names or server IDs for your specific needs.
Gridscale Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_WionY60yQsjgHzTZj8H9U0asZQd1c7pgU3MJvADr/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Gridscale capabilities are ready to use.
{
"mcpServers": {
"gridscale-iaas-paas-cloud-hosting-api-mcp": {
"url": "https://edge.vinkius.com/vk_preview_WionY60yQsjgHzTZj8H9U0asZQd1c7pgU3MJvADr/mcp"
}
}
}List all available server templates so I can choose one.
Create a new server using the 'ubuntu-22-04' template.
Link the IP address 192.168.1.50 to my new server.
Shut down the server with ID server-9928 to save costs.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Gridscale once, then ask.
One connection gives your AI client access to the full Gridscale API. Your credentials stay encrypted and secure.
Connect Gridscale to your AIFAQ
How this task behaves
- 01
Can the AI delete my servers?
No. There is no tool provided to delete or terminate servers, so the AI cannot remove your infrastructure.
- 02
Can the AI change my billing settings?
No. The AI only has access to provisioning and power management tools. It cannot touch your account or billing data.
- 03
Does the AI choose the server size for me?
The AI can suggest templates from the list, but you must confirm which one to use for the creation step.
- 04
Can I use this with any AI client?
Yes, as long as the client supports the Model Context Protocol (MCP).
- 05
Will the AI automatically scale my servers?
No. The AI only performs the specific actions you request, such as creating a single instance or changing power states.
More questions about Gridscale? The Connector page answers them. See everything the Gridscale Connector can do
Connect Gridscale to Claude, Cursor, ChatGPT & more
