AI agents use gandi_simplehosting_create_vhost to create or update resources in Gandi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gandi environment.
Creating a vhost is a reversible modification to a hosting configuration. It adds a new virtual host but does not execute arbitrary code, delete data, or commit financial transactions. The blast radius is moderate: misconfiguration could disrupt service availability or create unintended hosting configurations, but the action can be undone by deleting the vhost.
From the tool's definition Tool name contains 'create' and description states 'Create a vhost on a Simple Hosting instance' — this creates a new resource (virtual host) on an existing hosting instance.
Attacks that exploit this kind of access
Create a vhost on a Simple Hosting instance. It is categorised as a Write tool in the Gandi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_simplehosting_create_vhost: 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 Gandi. Nothing to install.
gandi_simplehosting_create_vhost is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gandi_simplehosting_create_vhost 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 gandi_simplehosting_create_vhost. 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.
gandi_simplehosting_create_vhost is provided by the Gandi MCP server (millsymills-com/gandi-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 →