prometheus_query_range · Overwatch MCP: Risk & Policy

WHAT IT DOES

What prometheus_query_range does on Overwatch MCP

AI agents invoke prometheus_query_range to trigger actions in Overwatch MCP. 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 prometheus_query_range needs a policy

The tool executes PromQL queries against Prometheus, which is an active execution of a query language. While it is primarily a read operation retrieving time series data, the use of 'Execute' in the description and the nature of running arbitrary PromQL expressions (which could be resource-intensive or access sensitive metrics) places it in the Execute category.

From the tool's definition Execute PromQL range query for time series data

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prometheus_query_range Rate-limited

prometheus_query_range 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": {
    "prometheus_query_range": {
      "limits": [
        {
          "counter": "prometheus_query_range_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 Overwatch MCP, so you can run agents against it safely.

FAQ

Questions about prometheus_query_range

What does the prometheus_query_range tool do? +

Execute PromQL range query for time series data. It is categorised as a Execute tool in the Overwatch MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on prometheus_query_range? +

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

What risk level is prometheus_query_range? +

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

Can I rate-limit prometheus_query_range? +

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

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

prometheus_query_range is provided by the Overwatch MCP server (malindarathnayake/overwatch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.