save_tensor · Tensorus MCP: Risk & Policy

WHAT IT DOES

What save_tensor does on Tensorus MCP

AI agents use save_tensor 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 save_tensor needs a policy

This tool creates or modifies tensor data within the Tensorus database. It does not execute arbitrary code, delete data irreversibly, move money, or merely read information. The action is reversible since tensors can be updated or removed in subsequent operations.

From the tool's definition Tool name 'save_tensor' and description 'Save a tensor to a dataset' indicates creation or modification of data in the tensor database.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_tensor Rate-limited

save_tensor 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": {
    "save_tensor": {
      "limits": [
        {
          "counter": "save_tensor_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 save_tensor

What does the save_tensor tool do? +

Save a tensor to a dataset. 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 save_tensor? +

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

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

Can I rate-limit save_tensor? +

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

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

save_tensor 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.