Start auth recovery against an explicit remote Yaver base URL when the caller is not signed into Yaver locally. Requires either bootstrap_secret or bearer_token. direct/device-code require bearer_token. Public HTTP targets are refused unless relay_password is provided or allow_public_direct_http=...
AI agents invoke recovery_target_start to trigger actions in Yaver. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | auto (default), direct, pair, or device-code. |
target_url | string | Yes | Exact remote base URL, e.g. https://edge.example.com or https://relay.example/d/device-id |
bearer_token | string | — | Host Yaver bearer token to use for direct or device-code recovery. |
relay_password | string | — | Optional relay password for private relay access. |
bootstrap_secret | string | — | Bootstrap secret previously configured on the remote machine. |
allow_public_direct_http | boolean | — | Unsafe override for plain public HTTP targets. Default false. |
Parameters from the server's own tool schema.
recovery_target_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Start auth recovery against an explicit remote Yaver base URL when the caller is not signed into Yaver locally. Requires either bootstrap_secret or bearer_token. direct/device-code require bearer_token. Public HTTP targets are refused unless relay_password is provided or allow_public_direct_http=true. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
recovery_target_start accepts 6 parameters: mode, target_url, bearer_token, relay_password, bootstrap_secret, allow_public_direct_http. Required: target_url. 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 recovery_target_start: 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.
recovery_target_start 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 recovery_target_start 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 recovery_target_start. 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.
recovery_target_start 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.