ask_database · Vanna AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What ask_database does on Vanna AI MCP Server

AI agents invoke ask_database to trigger actions in Vanna AI 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 ask_database needs a policy

The tool executes SQL queries generated from natural language, meaning the AI could produce and run unintended or harmful queries. While primarily a read/query tool in intent, the execution of AI-generated SQL is an Execute-category action with high blast radius if the generated SQL is destructive or data-exfiltrating.

From the tool's definition 'Vanna AI will convert it to SQL and execute it' — the tool both generates and runs arbitrary SQL against the database based on natural language input.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ask_database Rate-limited

ask_database 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": {
    "ask_database": {
      "limits": [
        {
          "counter": "ask_database_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 Vanna AI MCP Server, so you can run agents against it safely.

FAQ

Questions about ask_database

What does the ask_database tool do? +

Ask a natural language question about the database. Vanna AI will convert it to SQL and execute it. It is categorised as a Execute tool in the Vanna AI 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 ask_database? +

Register the Vanna AI MCP Server MCP server in PolicyLayer and add a rule for ask_database: 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 Vanna AI MCP Server. Nothing to install.

What risk level is ask_database? +

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

Can I rate-limit ask_database? +

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

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

ask_database is provided by the Vanna AI MCP Server MCP server (lilgreml1n/vanna-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.