One-shot install + auth + mobile-app handoff for a non-developer user being walked through setup by an AI agent. Call this FIRST instead of wiring up auth_status/start/wait manually. Returns a structured plan: whether yaver-cli is installed, whether the user is signed in, a sign-in URL (if needed...
AI agents use yaver_lazy_setup to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
wait_seconds | integer | — | If >0, block up to this many seconds (max 180) waiting for sign-in to complete in-call. Default 0 = return immediately. 120 is a reasonable value for agents tha |
Parameters from the server's own tool schema.
An AI agent can call yaver_lazy_setup faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
One-shot install + auth + mobile-app handoff for a non-developer user being walked through setup by an AI agent. Call this FIRST instead of wiring up auth_status/start/wait manually. Returns a structured plan: whether yaver-cli is installed, whether the user is signed in, a sign-in URL (if needed) the AI should surface to the human, mobile app install links (TestFlight + Play), and a single next_action string the AI can speak verbatim. Idempotent: safe to call repeatedly while the user finishes steps on their phone — on each call it picks up where the last one left off. The ideal orchestration loop for a coding agent: (1) call yaver_lazy_setup → show the returned url to the human; (2) wait a bit; (3) call yaver_lazy_setup again — if status is now "signed_in", you're done. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
yaver_lazy_setup accepts 1 parameter: wait_seconds. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for yaver_lazy_setup: 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 Yaver. Nothing to install.
yaver_lazy_setup 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 yaver_lazy_setup 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 yaver_lazy_setup. 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.
yaver_lazy_setup is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.