query_loki_logs · Mcp Grafana MCP: Risk & Policy

WHAT IT DOES

What query_loki_logs does on Mcp Grafana

AI agents invoke query_loki_logs to trigger actions in Mcp Grafana. 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 query_loki_logs needs a policy

The tool explicitly 'executes' a query, which is an active operation against an external datasource. While primarily read-oriented in outcome (retrieving logs/metrics), executing arbitrary LogQL queries against a datasource is an Execute-category action — the effects depend on the query arguments and it triggers external operations.

From the tool's definition 'Executes a LogQL query against a Loki datasource to retrieve log entries or metric values'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_loki_logs Rate-limited

query_loki_logs 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": {
    "query_loki_logs": {
      "limits": [
        {
          "counter": "query_loki_logs_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 Mcp Grafana, so you can run agents against it safely.

FAQ

Questions about query_loki_logs

What does the query_loki_logs tool do? +

Executes a LogQL query against a Loki datasource to retrieve log entries or metric values. It is categorised as a Execute tool in the Mcp Grafana MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_loki_logs? +

Register the Mcp Grafana MCP server in PolicyLayer and add a rule for query_loki_logs: 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 Mcp Grafana. Nothing to install.

What risk level is query_loki_logs? +

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

Can I rate-limit query_loki_logs? +

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

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

query_loki_logs is provided by the Mcp Grafana MCP server (@leval/mcp-grafana). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.