Poll a tab until a CSS selector appears or visible text is present, or timeout. Use after navigation or an action that triggers async rendering.
AI agents invoke wait_for to trigger actions in Nextjs Agent. 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 executes a browser operation that waits for and detects changes in the DOM state. While it does not delete data or move money, it actively triggers and monitors async rendering operations. It falls under Execute rather than Read because it performs polling and observation of dynamic browser state in response to actions, which can have timing-dependent effects on subsequent operations.
From the tool's definition The tool 'wait_for' polls a browser tab (via the DOM-based in-page bridge) until a CSS selector appears or visible text is present. It controls browser/DOM interactions with side effects that depend on what condition is being waited for.
Attacks that exploit this kind of access
Poll a tab until a CSS selector appears or visible text is present, or timeout. Use after navigation or an action that triggers async rendering. It is categorised as a Execute tool in the Nextjs Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nextjs Agent MCP server in PolicyLayer and add a rule for wait_for: 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 Nextjs Agent. Nothing to install.
wait_for 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 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. 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 is provided by the Nextjs Agent MCP server (zohaib3249/nextjs-agent-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 →