AI agents use create_destination to create or update resources in Zhook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zhook environment.
This tool creates a new destination configuration for forwarding events. It modifies the webhook system state by adding a new routing target, but the action is reversible (as evidenced by the delete_destination sibling tool). This is a Write operation: it creates/adds data without executing external commands or deleting information.
From the tool's definition Tool name 'create_destination' and description 'Add a new destination to a hook' indicate creation of a new configuration object. The verb 'Add' and context of managing webhook destinations shows data creation/modification.
Attacks that exploit this kind of access
Add a new destination to a hook to forward events to. It is categorised as a Write tool in the Zhook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zhook MCP server in PolicyLayer and add a rule for create_destination: 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 Zhook. Nothing to install.
create_destination 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 create_destination 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 create_destination. 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.
create_destination is provided by the Zhook MCP server (zhookteam/zhook-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 →