upsert_computational_metadata · Tensorus MCP: Risk & Policy

WHAT IT DOES

What upsert_computational_metadata does on Tensorus MCP

AI agents use upsert_computational_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_computational_metadata needs a policy

Upsert is fundamentally a Write operation: it inserts new metadata or updates existing metadata for a tensor descriptor. The operation is reversible (metadata can be corrected or deleted later). It does not execute arbitrary code, delete data irreversibly, or move money.

From the tool's definition Tool name contains 'upsert', which is a database operation that creates or modifies records. Description states 'Upsert computational metadata for a given tensor descriptor'—upsert is a reversible write operation (insert or update).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upsert_computational_metadata Rate-limited

upsert_computational_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_computational_metadata": {
      "limits": [
        {
          "counter": "upsert_computational_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_computational_metadata

What does the upsert_computational_metadata tool do? +

Upsert computational 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_computational_metadata? +

Register the Tensorus MCP server in PolicyLayer and add a rule for upsert_computational_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_computational_metadata? +

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

Can I rate-limit upsert_computational_metadata? +

Yes. Add a rate_limit block to the upsert_computational_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_computational_metadata completely? +

Set action: deny in the PolicyLayer policy for upsert_computational_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_computational_metadata? +

upsert_computational_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.