query_semantic · DB- MCP: Risk & Policy

WHAT IT DOES

What query_semantic does on DB-MCP

AI agents invoke query_semantic to trigger actions in DB-MCP. 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 query_semantic needs a policy

The tool executes queries against a data warehouse. While the server description mentions governance controls (PII blocking, access limits), arbitrary semantic query execution can expose sensitive data, perform expensive operations, or—depending on the underlying warehouse permissions—run destructive SQL. The most severe applicable category is Execute.

From the tool's definition "Execute governed semantic queries against the data warehouse"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_semantic Rate-limited

query_semantic 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": {
    "query_semantic": {
      "limits": [
        {
          "counter": "query_semantic_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 DB-MCP, so you can run agents against it safely.

FAQ

Questions about query_semantic

What does the query_semantic tool do? +

Execute governed semantic queries against the data warehouse. It is categorised as a Execute tool in the DB-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_semantic? +

Register the DB- MCP server in PolicyLayer and add a rule for query_semantic: 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 DB-MCP. Nothing to install.

What risk level is query_semantic? +

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

Can I rate-limit query_semantic? +

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

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

query_semantic is provided by the DB- MCP server (scrappymonkey/db-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.