summarize_metrics · OCI MCP Server MCP: Risk & Policy

WHAT IT DOES

What summarize_metrics does on OCI MCP Server

AI agents invoke summarize_metrics to trigger actions in OCI MCP Server. 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.

WHY IT NEEDS A POLICY

Why summarize_metrics needs a policy

The tool actively executes a query (MQL) against OCI's monitoring service to retrieve metric data. While the result is read-like (metrics/telemetry data), the action is 'Run a MQL summary' which constitutes executing a query expression against an external system. Since it executes arbitrary MQL expressions on OCI infrastructure, it falls under Execute rather than Read.

From the tool's definition 'Run a MQL summary' — executes a Monitoring Query Language (MQL) query against OCI metrics infrastructure

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

summarize_metrics Rate-limited

summarize_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": {
    "summarize_metrics": {
      "limits": [
        {
          "counter": "summarize_metrics_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about summarize_metrics

What does the summarize_metrics tool do? +

Run a MQL summary. Times: ISO8601. Query: e.g. 'CpuUtilization[1m].mean()'. It is categorised as a Execute tool in the OCI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on summarize_metrics? +

Register the OCI MCP Server MCP server in PolicyLayer and add a rule for summarize_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 OCI MCP Server. Nothing to install.

What risk level is summarize_metrics? +

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

Can I rate-limit summarize_metrics? +

Yes. Add a rate_limit block to the summarize_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 summarize_metrics completely? +

Set action: deny in the PolicyLayer policy for summarize_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 summarize_metrics? +

summarize_metrics is provided by the OCI MCP Server MCP server (sarthak-pansare/oci-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.