Re-auth on the user's primary remote device. With runner empty (default) this refreshes the Yaver session token via the existing /auth/recover flow (same as yaver primary auth). With runner=claude or codex, it kicks off the runner's browser/device-code login flow on the primary box (same as yaver...
AI agents call primary_auth to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
runner | string | — | Empty (default) for Yaver-level reauth; claude/claude-code or codex to start that runner's login flow on the primary device. |
Parameters from the server's own tool schema.
Even though primary_auth only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Re-auth on the user's primary remote device. With runner empty (default) this refreshes the Yaver session token via the existing /auth/recover flow (same as yaver primary auth). With runner=claude or codex, it kicks off the runner's browser/device-code login flow on the primary box (same as yaver primary auth claude / yaver primary auth codex); the response carries the URL/code the user opens to finish. Resolves the primary deviceId automatically — no need to look it up first. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
primary_auth accepts 1 parameter: runner. 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 primary_auth: 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.
primary_auth is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the primary_auth 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 primary_auth. 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.
primary_auth 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.