execute_async_query · Imply Druid MCP: Risk & Policy

WHAT IT DOES

What execute_async_query does on Imply Druid

AI agents invoke execute_async_query to trigger actions in Imply Druid. 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 execute_async_query needs a policy

Although the server is read-only (limiting destructive potential), executing arbitrary SQL queries is an Execute action that can retrieve data, trigger database operations, and consume resources. The async nature and ability to run 'long-running queries' on 'large datasets' increases the blast radius if an agent constructs malicious queries.

From the tool's definition Tool name is 'execute_async_query' and description states it 'Execute[s] an asynchronous SQL query'. The server is described as 'read-only' and this tool executes SQL queries, which qualifies as Execute category—running code whose effects depend on the query…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_async_query Rate-limited

execute_async_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": {
    "execute_async_query": {
      "limits": [
        {
          "counter": "execute_async_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 Imply Druid, so you can run agents against it safely.

FAQ

Questions about execute_async_query

What does the execute_async_query tool do? +

Execute an asynchronous SQL query for large datasets or long-running queries. Returns a query ID. It is categorised as a Execute tool in the Imply Druid MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_async_query? +

Register the Imply Druid MCP server in PolicyLayer and add a rule for execute_async_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 Imply Druid. Nothing to install.

What risk level is execute_async_query? +

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

Can I rate-limit execute_async_query? +

Yes. Add a rate_limit block to the execute_async_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 execute_async_query completely? +

Set action: deny in the PolicyLayer policy for execute_async_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 execute_async_query? +

execute_async_query is provided by the Imply Druid MCP server (yeongbin-hwang/imply-druid-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.