Get a tensor descriptor by its ID.
AI agents call get_tensor_descriptor to retrieve information from Tensorus MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about a tensor by its identifier. It performs a read-only query operation without creating, modifying, deleting, or executing anything. The low severity reflects the minimal blast radius: an agent misusing this tool can only access descriptor information it is already authorized to view, with no ability to alter data or trigger external operations.
From the tool's definition Tool name is 'get_tensor_descriptor' and description states 'Get a tensor descriptor by its ID' — this is a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get a tensor descriptor by its ID. It is categorised as a Read tool in the Tensorus MCP MCP Server, which means it retrieves data without modifying state.
Register the Tensorus MCP server in PolicyLayer and add a rule for get_tensor_descriptor: 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.
get_tensor_descriptor is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_tensor_descriptor 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.
Set action: deny in the PolicyLayer policy for get_tensor_descriptor. 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.
get_tensor_descriptor 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →