AI agents invoke wait to trigger actions in MacWright. 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.
While wait() itself is a benign operation with no direct side effects on data or system state, it is an executable control flow instruction that triggers system-level timer functionality. It falls into Execute rather than Read because it actively runs/triggers an operation (a timed pause) whose effect is to control program execution timing.
From the tool's definition Tool name 'wait' and description states it 'pause[s] execution for the specified number of milliseconds', which triggers a programmatic operation (timer/sleep) that delays subsequent actions.
Attacks that exploit this kind of access
Pause execution for the specified number of milliseconds. Useful for waiting for animations, page loads, or UI transitions to complete before taking the next action. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright MCP server in PolicyLayer and add a rule for wait: 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 MacWright. Nothing to install.
wait 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 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. 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 is provided by the MacWright MCP server (ruchit-p/macwright). 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 →