ops_plan · Yaver MCP: Risk & Policy

WHAT IT DOES

What ops_plan does on Yaver

AI agents use ops_plan to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

PARAMETERS

Parameter	Type	Required	Description
`verb`	string	Yes	Verb name to plan for.
`machine`	string	—	Target: "local", "auto", "primary", or a deviceId / alias. Same semantics as `ops`.
`payload`	object	—	Verb-specific payload used for workDir / target / placement inference.

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why ops_plan needs a policy

An AI agent can call ops_plan faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.

Risk signalsAccepts raw HTML/template content (payload)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ops_plan Rate-limited

ops_plan stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ops_plan": {
      "limits": [
        {
          "counter": "ops_plan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yaver, so you can run agents against it safely.

FAQ

Questions about ops_plan

What does the ops_plan tool do? +

Resolve the execution plan for one ops verb without running it. Returns project context, machine placement, and caller access policy so agents can inspect deploy/reload routing and guest/share constraints ahead of time. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does ops_plan accept? +

ops_plan accepts 3 parameters: verb, machine, payload. Required: verb. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on ops_plan? +

Register the Yaver MCP server in PolicyLayer and add a rule for ops_plan: 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.

What risk level is ops_plan? +

ops_plan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ops_plan? +

Yes. Add a rate_limit block to the ops_plan 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.

How do I block ops_plan completely? +

Set action: deny in the PolicyLayer policy for ops_plan. 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.

What MCP server provides ops_plan? +

ops_plan 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.