tensorus_ingest_tensor · Tensorus MCP: Risk & Policy

WHAT IT DOES

What tensorus_ingest_tensor does on Tensorus MCP

AI agents use tensorus_ingest_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 tensorus_ingest_tensor needs a policy

This tool creates or adds new tensor data to a dataset, which is a reversible write operation. It does not retrieve data (Read), execute arbitrary code (Execute), permanently delete data (Destructive), or transfer funds (Financial). The severity is medium because uncontrolled tensor ingestion could consume storage resources or corrupt dataset integrity, but the operation is reversible.

From the tool's definition Tool name 'tensorus_ingest_tensor' and description 'Ingest a new tensor into a dataset' indicate creation of new data within the tensor database. 'Ingest' is a data insertion operation that modifies dataset state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tensorus_ingest_tensor Rate-limited

tensorus_ingest_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": {
    "tensorus_ingest_tensor": {
      "limits": [
        {
          "counter": "tensorus_ingest_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 tensorus_ingest_tensor

What does the tensorus_ingest_tensor tool do? +

Ingest a new tensor into 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 tensorus_ingest_tensor? +

Register the Tensorus MCP server in PolicyLayer and add a rule for tensorus_ingest_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 tensorus_ingest_tensor? +

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

Can I rate-limit tensorus_ingest_tensor? +

Yes. Add a rate_limit block to the tensorus_ingest_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 tensorus_ingest_tensor completely? +

Set action: deny in the PolicyLayer policy for tensorus_ingest_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 tensorus_ingest_tensor? +

tensorus_ingest_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.