upsert_quality_metadata · Tensorus MCP: Risk & Policy

WHAT IT DOES

What upsert_quality_metadata does on Tensorus MCP

AI agents use upsert_quality_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_quality_metadata needs a policy

Upsert is a standard write operation that creates or modifies metadata without deleting underlying data or executing arbitrary code. The blast radius is moderate because metadata corruption could affect data quality assessment and downstream tensor operations, but the operation itself is reversible (metadata can be corrected or overwritten).

From the tool's definition Tool name 'upsert_quality_metadata' uses 'upsert' (update or insert), a reversible modification operation on metadata associated with tensor descriptors.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upsert_quality_metadata Rate-limited

upsert_quality_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_quality_metadata": {
      "limits": [
        {
          "counter": "upsert_quality_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_quality_metadata

What does the upsert_quality_metadata tool do? +

Upsert quality 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_quality_metadata? +

Register the Tensorus MCP server in PolicyLayer and add a rule for upsert_quality_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_quality_metadata? +

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

Can I rate-limit upsert_quality_metadata? +

Yes. Add a rate_limit block to the upsert_quality_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_quality_metadata completely? +

Set action: deny in the PolicyLayer policy for upsert_quality_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_quality_metadata? +

upsert_quality_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.