kusto_execute · Kusto MCP Server MCP: Risk & Policy

WHAT IT DOES

What kusto_execute does on Kusto MCP Server

AI agents invoke kusto_execute to trigger actions in Kusto 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 kusto_execute needs a policy

This tool allows execution of arbitrary Kusto commands with full CLI flexibility, not just read queries. Kusto's control command language includes commands that can modify database state, drop tables, alter schemas, and perform administrative operations. While the tool itself doesn't strictly delete data, it has the capability to execute destructive commands depending on what an AI agent submits.

From the tool's definition Tool description states: 'Execute advanced Kusto commands with full CLI options. Use this for control commands, multiple statements, or when you need fine-grained control.' The verb 'Execute' and references to 'advanced Kusto commands' and 'control commands'…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kusto_execute Rate-limited

kusto_execute 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": {
    "kusto_execute": {
      "limits": [
        {
          "counter": "kusto_execute_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 Kusto MCP Server, so you can run agents against it safely.

FAQ

Questions about kusto_execute

What does the kusto_execute tool do? +

Execute advanced Kusto commands with full CLI options. Use this for control commands, multiple statements, or when you need fine-grained control. It is categorised as a Execute tool in the Kusto 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 kusto_execute? +

Register the Kusto MCP Server MCP server in PolicyLayer and add a rule for kusto_execute: 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 Kusto MCP Server. Nothing to install.

What risk level is kusto_execute? +

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

Can I rate-limit kusto_execute? +

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

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

kusto_execute is provided by the Kusto MCP Server MCP server (yeshsurya/kusto-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.