tensorus_apply_unary_operation · Tensorus MCP: Risk & Policy

WHAT IT DOES

What tensorus_apply_unary_operation does on Tensorus MCP

AI agents invoke tensorus_apply_unary_operation to trigger actions in Tensorus MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why tensorus_apply_unary_operation needs a policy

This tool executes a computation (a unary operation like log or reshape) on tensor data. It doesn't merely read data, nor does it irreversibly delete it. It runs an operation whose effects depend on the arguments passed, placing it squarely in the Execute category. Severity is medium because misuse could corrupt or misshape tensor data, but the effects may be recoverable depending on the system's design.

From the tool's definition 'Apply a unary TensorOps operation (e.g., log, reshape)' — triggers an external tensor computation operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tensorus_apply_unary_operation Rate-limited

tensorus_apply_unary_operation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tensorus_apply_unary_operation": {
      "limits": [
        {
          "counter": "tensorus_apply_unary_operation_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 tensorus_apply_unary_operation

What does the tensorus_apply_unary_operation tool do? +

Apply a unary TensorOps operation (e.g., log, reshape). It is categorised as a Execute tool in the Tensorus MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tensorus_apply_unary_operation? +

Register the Tensorus MCP server in PolicyLayer and add a rule for tensorus_apply_unary_operation: 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 tensorus_apply_unary_operation? +

tensorus_apply_unary_operation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit tensorus_apply_unary_operation? +

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

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

tensorus_apply_unary_operation 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.