upsert_item · NeuronSearchLab MCP: Risk & Policy

WHAT IT DOES

What upsert_item does on NeuronSearchLab

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

WHY IT NEEDS A POLICY

Why upsert_item needs a policy

This tool modifies catalogue data but does not irreversibly delete it (which would be Destructive), does not execute arbitrary code (Execute), does not move money (Financial), and is not merely a read operation (Read). The blast radius is moderate—incorrect catalogue entries could degrade recommendation quality or expose bad data, but the operation is reversible by updating or deleting the item via other means.

From the tool's definition Tool name is 'upsert_item' and description states it can 'Add or update an item in the recommendation catalogue.' Upsert (update-or-insert) is a reversible write operation that creates or modifies data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upsert_item Rate-limited

upsert_item 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": {
    "upsert_item": {
      "limits": [
        {
          "counter": "upsert_item_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 NeuronSearchLab, so you can run agents against it safely.

FAQ

Questions about upsert_item

What does the upsert_item tool do? +

Add or update an item in the recommendation catalogue. It is categorised as a Write tool in the NeuronSearchLab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upsert_item? +

Register the NeuronSearchLab MCP server in PolicyLayer and add a rule for upsert_item: 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 NeuronSearchLab. Nothing to install.

What risk level is upsert_item? +

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

Can I rate-limit upsert_item? +

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

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

upsert_item is provided by the NeuronSearchLab MCP server (neuronsearchlab/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.