ops
Run one verb on one machine. Single API for every Yaver capability (info, run, build, test, deploy, push, reload, logs, status, env, session, scale, provision, destroy, ...). Discover available verbs via ops_verbs.
This record as markdown: /tools/io-github-kivanccakmak-yaver/ops.md
What ops does on Yaver
AI agents invoke ops 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 |
|---|---|---|---|
verb | string | Yes | Verb name. Call ops_verbs for the registered list + each verb's payload schema. |
machine | string | — | Target: "local", "auto", "primary", or a deviceId / alias. Cross-machine routing is supported; "auto" uses project-aware placement for deploy/reload and otherwi |
payload | object | — | Verb-specific payload. Shape depends on verb. |
Parameters from the server's own tool schema.
Why ops is rated High
This tool is a unified execution interface that can trigger a wide range of operations on machines, including irreversible ones like 'destroy' and high-impact ones like 'deploy', 'scale', and 'provision'. Because it wraps Financial-adjacent (provision/scale cost), Destructive (destroy), and Execute (run/build/deploy) capabilities in a single call, it warrants critical severity.
From the tool's definition 'Run one verb on one machine. Single API for every Yaver capability (info, run, build, test, deploy, push, reload, logs, status, env, session, scale, provision, destroy, ...)' — explicitly includes destructive and high-impact verbs like 'destroy', 'deploy',…
Risk signalsAccepts raw HTML/template content (payload) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs ops 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 ops, this is the rule to start with:
ops 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 ops call is checked against it from then on.
Questions about ops
Run one verb on one machine. Single API for every Yaver capability (info, run, build, test, deploy, push, reload, logs, status, env, session, scale, provision, destroy, ...). Discover available verbs via ops_verbs. 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.
ops accepts 3 parameters: verb, machine, payload. Required: verb. 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 ops: 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.
ops 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 ops 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 ops. 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.
ops 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