vector_store_add · Vending Machine MCP: Risk & Policy

WHAT IT DOES

What vector_store_add does on Vending Machine

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

WHY IT NEEDS A POLICY

Why vector_store_add needs a policy

The tool performs a write operation by adding entries to a vector store, which creates or modifies data. This is reversible (items can typically be removed later), so it does not qualify as Destructive.

From the tool's definition Tool name 'vector_store_add' indicates it adds data to a vector store. The description is empty, limiting direct evidence, but the naming pattern and the server's context (managing vector stores) suggests a data modification operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vector_store_add Rate-limited

vector_store_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_store_add": {
      "limits": [
        {
          "counter": "vector_store_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 Vending Machine, so you can run agents against it safely.

FAQ

Questions about vector_store_add

What does the vector_store_add tool do? +

vector_store_add. It is categorised as a Write tool in the Vending Machine 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_store_add? +

Register the Vending Machine MCP server in PolicyLayer and add a rule for vector_store_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 Vending Machine. Nothing to install.

What risk level is vector_store_add? +

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

Can I rate-limit vector_store_add? +

Yes. Add a rate_limit block to the vector_store_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_store_add completely? +

Set action: deny in the PolicyLayer policy for vector_store_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_store_add? +

vector_store_add is provided by the Vending Machine MCP server (yokiidesu/vending-machine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

vector_store_add is one line of Vending Machine's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →