infra_power
Run a managed power action. ALWAYS call action=report first: it is a read-only dry run that says which power actions this machine can actually perform, what each would really do (a container 'reboot' is not a host reboot), the exact command, and the recovery ETA. report needs no confirm; host_reb...
This record as markdown: /tools/io-github-kivanccakmak-yaver/infra-power.md
What infra_power does on Yaver
AI agents invoke infra_power 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 | Yes | report = read-only capability dry run. host_reboot = power-cycle the machine. agent_restart = restart just the Yaver agent, machine stays up. agent_shutdown = s |
confirm | boolean | — | Must be true for every action except report |
Parameters from the server's own tool schema.
Why infra_power is rated High
This tool executes system-level power management commands (reboot, restart, shutdown) that alter the state of infrastructure. While the 'report' action is read-only, the tool's primary purpose is to execute power actions that have real side effects on system availability and state.
From the tool's definition Tool description states it can 'Run a managed power action' including 'host_reboot', 'agent_restart' and 'agent_shutdown' which are system-level operations that trigger external processes with significant effects.
Attacks that exploit this kind of access
The rule that runs infra_power 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 infra_power, this is the rule to start with:
infra_power 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 infra_power call is checked against it from then on.
Questions about infra_power
Run a managed power action. ALWAYS call action=report first: it is a read-only dry run that says which power actions this machine can actually perform, what each would really do (a container 'reboot' is not a host reboot), the exact command, and the recovery ETA. report needs no confirm; host_reboot, agent_restart and agent_shutdown all require confirm=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.
infra_power accepts 2 parameters: action, confirm. Required: action. 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 infra_power: 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.
infra_power 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 infra_power 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 infra_power. 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.
infra_power 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