vector_add · LanceDB Node MCP: Risk & Policy

WHAT IT DOES

What vector_add does on LanceDB Node

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

WHY IT NEEDS A POLICY

Why vector_add needs a policy

This tool creates or modifies data in a vector database in a reversible manner. New vectors can be added, updated, or removed without permanent destruction. It does not execute arbitrary code, delete data irreversibly, or move money.

From the tool's definition Tool adds vectors with metadata to a LanceDB table and can create the table if it doesn't exist. The description explicitly states 'Add vectors' and 'Creates the table if it doesn', indicating data creation and modification capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vector_add Rate-limited

vector_add 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": {
    "vector_add": {
      "limits": [
        {
          "counter": "vector_add_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 LanceDB Node, so you can run agents against it safely.

FAQ

Questions about vector_add

What does the vector_add tool do? +

Add vectors with metadata to a LanceDB table. Creates the table if it doesn. It is categorised as a Write tool in the LanceDB Node MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vector_add? +

Register the LanceDB Node MCP server in PolicyLayer and add a rule for vector_add: 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 LanceDB Node. Nothing to install.

What risk level is vector_add? +

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

Can I rate-limit vector_add? +

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

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

vector_add is provided by the LanceDB Node MCP server (vurtnec/mcp-lancedb-node). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.