ons_upsert · Open Neural Substrate MCP: Risk & Policy

WHAT IT DOES

What ons_upsert does on Open Neural Substrate

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

WHY IT NEEDS A POLICY

Why ons_upsert needs a policy

Upsert operations are reversible writes that create or modify data records. In a knowledge graph context, this tool would add or update neuron entries, making it a Write risk. Severity is high because unauthorized upserts to a persistent knowledge graph could corrupt or poison the stored knowledge that Claude relies on.

From the tool's definition Tool name 'ons_upsert' (upsert = update or insert) and context as a knowledge graph management system indicates create/modify operations on persistent data. The sibling tools include ons_delete and ons_rewire, confirming this is a data mutation system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ons_upsert Rate-limited

ons_upsert 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": {
    "ons_upsert": {
      "limits": [
        {
          "counter": "ons_upsert_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 Open Neural Substrate, so you can run agents against it safely.

FAQ

Questions about ons_upsert

What does the ons_upsert tool do? +

ons_upsert. It is categorised as a Write tool in the Open Neural Substrate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ons_upsert? +

Register the Open Neural Substrate MCP server in PolicyLayer and add a rule for ons_upsert: 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 Open Neural Substrate. Nothing to install.

What risk level is ons_upsert? +

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

Can I rate-limit ons_upsert? +

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

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

ons_upsert is provided by the Open Neural Substrate MCP server (pedroknigge/open-neural-substrate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.