Manage cloud provider tokens (Hetzner/DigitalOcean): list/get/create/update/delete/validate
AI agents call cloud_tokens to permanently remove resources in Coolify — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly includes 'delete' operations on cloud provider authentication tokens (Hetzner/DigitalOcean). Deleting or invalidating cloud provider tokens could irreversibly disrupt infrastructure access and all dependent services. It also includes create/update (Write) and list/get (Read), but the most severe applicable category is Destructive due to the delete capability.
From the tool's definition Manage cloud provider tokens: list/get/create/update/delete/validate
Attacks that exploit this kind of access
Manage cloud provider tokens (Hetzner/DigitalOcean): list/get/create/update/delete/validate. It is categorised as a Destructive tool in the Coolify MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Coolify MCP server in PolicyLayer and add a rule for cloud_tokens: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Coolify. Nothing to install.
cloud_tokens is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cloud_tokens rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cloud_tokens. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cloud_tokens is provided by the Coolify MCP server (jurislm/coolify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →