AI agents invoke wait_for_event to trigger actions in Zhook. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool initiates an active WebSocket connection and waits for an external event, triggering an external operation (network connection, blocking wait) whose outcome depends on runtime arguments. It is more than a simple passive read — it establishes a live connection and blocks execution for up to 60 seconds, placing it in the Execute category.
From the tool's definition Connects to the Zhook WebSocket and waits for the NEXT event to arrive on a specific hook. Returns the full event payload immediately. TIMEOUT is 60 seconds.
Attacks that exploit this kind of access
Connects to the Zhook WebSocket and waits for the NEXT event to arrive on a specific hook. Returns the full event payload immediately. TIMEOUT is 60 seconds. It is categorised as a Execute tool in the Zhook MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zhook MCP server in PolicyLayer and add a rule for wait_for_event: 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.
wait_for_event is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the wait_for_event 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 wait_for_event. 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.
wait_for_event 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 →