machine_repair
Deterministically repair an owned machine. restart_agent asks this connected watchdog agent to use Yaver's backup SSH/mesh channel to restart the target's Yaver agent, then callers should re-run machine_doctor or machine_roles_doctor.
This record as markdown: /tools/io-github-kivanccakmak-yaver/machine-repair.md
What machine_repair does on Yaver
AI agents invoke machine_repair 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 |
|---|---|---|---|
action | string | — | restart_agent is currently the only supported repair. |
device | string | — | Alias or name for the target device. |
deviceId | string | — | Target device ID, alias, or name. |
Parameters from the server's own tool schema.
Why machine_repair is rated High
This tool executes commands on a remote machine via SSH/mesh infrastructure to restart a watchdog agent. While the operation is bounded (restart only, not arbitrary code), it triggers external side effects on another system whose outcome depends on the machine's state. This is Execute rather than Write because it invokes system-level operations and remote agent restarts, not merely data creation/modification.
From the tool's definition Tool description states it performs agent restart via 'backup SSH/mesh channel' and triggers repair operations. The phrase 'restart_agent' and 'restart the target's Yaver agent' indicates execution of remote operations on a connected machine.
Attacks that exploit this kind of access
The rule that runs machine_repair safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For machine_repair, this is the rule to start with:
machine_repair stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every machine_repair call is checked against it from then on.
Questions about machine_repair
Deterministically repair an owned machine. restart_agent asks this connected watchdog agent to use Yaver's backup SSH/mesh channel to restart the target's Yaver agent, then callers should re-run machine_doctor or machine_roles_doctor. 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.
machine_repair accepts 3 parameters: action, device, deviceId. 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 machine_repair: 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.
machine_repair 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 machine_repair 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 machine_repair. 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.
machine_repair 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.
More on Yaver, and thousands of servers like it.
Across the catalogue