train_vanna · Vanna AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What train_vanna does on Vanna AI MCP Server

AI agents use train_vanna to create or update resources in Vanna AI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vanna AI MCP Server environment.

WHY IT NEEDS A POLICY

Why train_vanna needs a policy

This tool modifies the Vanna AI model's training data by adding DDL statements, documentation, or SQL examples to ChromaDB persistent storage. It creates/updates stored patterns that influence future query generation. This is a Write operation as it persistently modifies the AI model's knowledge base, but is not irreversibly destructive (training data can typically be removed).

From the tool's definition Train Vanna AI with DDL, documentation, or example queries to improve accuracy

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

train_vanna Rate-limited

train_vanna stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "train_vanna": {
      "limits": [
        {
          "counter": "train_vanna_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 train_vanna

What does the train_vanna tool do? +

Train Vanna AI with DDL, documentation, or example queries to improve accuracy. It is categorised as a Write tool in the Vanna AI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on train_vanna? +

Register the Vanna AI MCP Server MCP server in PolicyLayer and add a rule for train_vanna: 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 train_vanna? +

train_vanna is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit train_vanna? +

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

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

train_vanna 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.