Delete a tensor descriptor by its ID.
AI agents call delete_tensor_descriptor to permanently remove resources in Tensorus MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs deletion of a descriptor, which cannot be undone and represents permanent loss of data structure. While it may not delete the tensor data itself (only its descriptor), the removal of metadata is a destructive action that could break lineage, discovery, or indexing within the system.
From the tool's definition Tool name explicitly contains 'delete' and description states 'Delete a tensor descriptor by its ID.' This is an irreversible operation that removes metadata from the tensor database.
Attacks that exploit this kind of access
Delete a tensor descriptor by its ID. It is categorised as a Destructive tool in the Tensorus MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tensorus MCP server in PolicyLayer and add a rule for delete_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.
delete_tensor_descriptor is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_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 delete_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.
delete_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 →