Runs KQL queries and returns results. By default, limits results to 20 rows to prevent context overflow. Use the
AI agents invoke execute-query to trigger actions in Kusto. 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.
The tool executes arbitrary KQL queries provided by the user/agent. While KQL is primarily read-oriented, the ability to execute dynamic queries against a database—especially one that could potentially be misconfigured to allow data modification or destructive operations—constitutes an Execute risk. An AI agent could be tricked into running unintended queries that modify or delete data if the user has permissions.
From the tool's definition Tool description states it 'Runs KQL queries' - this directly indicates execution of code queries against a database. KQL (Kusto Query Language) is a query language for Azure Data Explorer that can perform complex data operations.
Documented attack patterns abuse exactly the kind of access execute-query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kusto, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-query:
{
"version": "1",
"default": "deny",
"tools": {
"execute-query": {
"limits": [
{
"counter": "execute-query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-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.
Free to start. No card required.
Runs KQL queries and returns results. By default, limits results to 20 rows to prevent context overflow. Use the. It is categorised as a Execute tool in the Kusto MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kusto MCP server in PolicyLayer and add a rule for execute-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 Kusto. Nothing to install.
execute-query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute-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.
Set action: deny in the PolicyLayer policy for execute-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.
execute-query is provided by the Kusto MCP server (johnib/kusto-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kusto, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Kusto tools catalogued and risk-classified — across an index of 43,000+ MCP servers.