azure_query · MCP Container Tools MCP: Risk & Policy

WHAT IT DOES

What azure_query does on MCP Container Tools

AI agents invoke azure_query to trigger actions in MCP Container Tools. 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 azure_query needs a policy

The tool executes arbitrary Kusto Query Language (KQL) expressions against Azure Application Insights. While Application Insights is primarily a read/analytics service, executing arbitrary queries poses significant risk: a malicious or misconfigured query could exfiltrate sensitive telemetry, traces, secrets logged in application data, or be used for reconnaissance.

From the tool's definition 'Run a custom Kusto query on Application Insights logs' — executes arbitrary user-supplied Kusto queries against cloud telemetry data

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

azure_query Rate-limited

azure_query 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": {
    "azure_query": {
      "limits": [
        {
          "counter": "azure_query_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 Container Tools, so you can run agents against it safely.

FAQ

Questions about azure_query

What does the azure_query tool do? +

Run a custom Kusto query on Application Insights logs. It is categorised as a Execute tool in the MCP Container Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on azure_query? +

Register the MCP Container Tools MCP server in PolicyLayer and add a rule for azure_query: 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 Container Tools. Nothing to install.

What risk level is azure_query? +

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

Can I rate-limit azure_query? +

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

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

azure_query is provided by the MCP Container Tools MCP server (simseksem/mcp-container-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.