execute_query · Spark SQL MCP: Risk & Policy

WHAT IT DOES

What execute_query does on Spark SQL

AI agents invoke execute_query to trigger actions in Spark SQL. 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_query needs a policy

The tool runs SQL statements on a live Spark/Hive cluster. While described as read-only, arbitrary SQL execution carries inherent risk: enforcement of read-only constraints depends entirely on the server-side implementation and credentials used. A misconfigured or manipulated query could trigger expensive scans, expose sensitive data, or—if the read-only claim is not enforced—perform writes or drops.

From the tool's definition "Execute a read-only Spark SQL query" — the name 'execute_query' and the verb 'Execute' indicate running arbitrary SQL against a live cluster; 'read-only' is a stated intent but is not an enforceable guarantee at the protocol level.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_query Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_query": {
      "limits": [
        {
          "counter": "execute_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 Spark SQL, so you can run agents against it safely.

FAQ

Questions about execute_query

What does the execute_query tool do? +

Execute a read-only Spark SQL query and return results as a formatted table. It is categorised as a Execute tool in the Spark SQL 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_query? +

Register the Spark SQL 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 Spark SQL. Nothing to install.

What risk level is execute_query? +

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

Can I rate-limit execute_query? +

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.

How do I block execute_query completely? +

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.

What MCP server provides execute_query? +

execute_query is provided by the Spark SQL MCP server (spark-sql-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.