ai_plan_metrics

Run a sample of planner goals against the on-device Foundation Model and report the aggregate score.

SERVERAirMCP SOURCEairmcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/heznpc-airmcp/ai-plan-metrics.md

WHAT IT DOES

What ai_plan_metrics does on AirMCP

AI agents invoke ai_plan_metrics to trigger actions in AirMCP. 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.

RISK

Why ai_plan_metrics is rated High

The tool executes inference runs against the on-device Foundation Model, triggering external computation. It is not a simple read/query of static data — it actively runs a workload and produces derived results. The blast radius is medium since it consumes local compute resources and could potentially be used to run many inference calls, but it does not modify persistent data or cause financial harm.

From the tool's definition "Run a sample of planner goals against the on-device Foundation Model and report the aggregate score"

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ai_plan_metrics safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ai_plan_metrics, this is the rule to start with:

ai_plan_metrics Rate-limited

ai_plan_metrics 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ai_plan_metrics": {
      "limits": [
        {
          "counter": "ai_plan_metrics_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every ai_plan_metrics call is checked against it from then on.

FAQ

Questions about ai_plan_metrics

What does the ai_plan_metrics tool do? +

Run a sample of planner goals against the on-device Foundation Model and report the aggregate score. It is categorised as a Execute tool in the AirMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ai_plan_metrics? +

Register the Air MCP server in PolicyLayer and add a rule for ai_plan_metrics: 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 AirMCP. Nothing to install.

What risk level is ai_plan_metrics? +

ai_plan_metrics is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ai_plan_metrics? +

Yes. Add a rate_limit block to the ai_plan_metrics 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 ai_plan_metrics completely? +

Set action: deny in the PolicyLayer policy for ai_plan_metrics. 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 ai_plan_metrics? +

ai_plan_metrics is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Air, and thousands of servers like it.

This server

All 279 Air tools → High-risk tools on this server →

Across the catalogue

team_manager_approve_plan on Team Manager MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →