upsert_relational_metadata · Tensorus MCP: Risk & Policy

WHAT IT DOES

What upsert_relational_metadata does on Tensorus MCP

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

WHY IT NEEDS A POLICY

Why upsert_relational_metadata needs a policy

Upserting metadata modifies data in the Tensorus tensor database in a reversible way. It is not a Read operation (no pure query), not Destructive (metadata can be re-upserted), not Execute (does not run arbitrary code or commands), and not Financial.

From the tool's definition Tool name contains 'upsert' which is a Write operation (create or update reversibly). Description states 'Upsert relational metadata for a given tensor descriptor' - upsert is a standard database operation that inserts new records or updates existing ones…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upsert_relational_metadata Rate-limited

upsert_relational_metadata 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_relational_metadata": {
      "limits": [
        {
          "counter": "upsert_relational_metadata_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 Tensorus MCP, so you can run agents against it safely.

FAQ

Questions about upsert_relational_metadata

What does the upsert_relational_metadata tool do? +

Upsert relational metadata for a given tensor descriptor. It is categorised as a Write tool in the Tensorus MCP 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_relational_metadata? +

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

What risk level is upsert_relational_metadata? +

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

Can I rate-limit upsert_relational_metadata? +

Yes. Add a rate_limit block to the upsert_relational_metadata 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_relational_metadata completely? +

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

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