monitoring_record_metric · AgentOS MCP: Risk & Policy

WHAT IT DOES

What monitoring_record_metric does on AgentOS

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

WHY IT NEEDS A POLICY

Why monitoring_record_metric needs a policy

This tool writes metric data to a monitoring or logging system. Recording a metric is a write operation (creating a new data point), with no indication of code execution, deletion, or financial impact. Misuse potential is low since metrics are generally append-only observational data.

From the tool's definition 'Record a performance or business metric' — creates/writes a new metric entry

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

monitoring_record_metric Rate-limited

monitoring_record_metric 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": {
    "monitoring_record_metric": {
      "limits": [
        {
          "counter": "monitoring_record_metric_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 AgentOS, so you can run agents against it safely.

FAQ

Questions about monitoring_record_metric

What does the monitoring_record_metric tool do? +

Record a performance or business metric. It is categorised as a Write tool in the AgentOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on monitoring_record_metric? +

Register the AgentOS MCP server in PolicyLayer and add a rule for monitoring_record_metric: 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 AgentOS. Nothing to install.

What risk level is monitoring_record_metric? +

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

Can I rate-limit monitoring_record_metric? +

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

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

monitoring_record_metric is provided by the AgentOS MCP server (netflypsb/agentos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

monitoring_record_metric is one line of AgentOS's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →