Delete an object in a bucket
AI agents call tigris_delete_object to permanently remove resources in Tigris — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes objects from cloud storage without the ability to undo the action. Destructive is the appropriate classification because deletion is irreversible. Severity is high because accidental or malicious use could cause permanent data loss affecting business continuity, though blast radius depends on the sensitivity of stored objects.
From the tool's definition Tool name and description: 'Delete an object in a bucket' — the word 'delete' combined with the action of removing an object from storage indicates an irreversible data destruction operation.
Attacks that exploit this kind of access
Delete an object in a bucket. It is categorised as a Destructive tool in the Tigris MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tigris MCP server in PolicyLayer and add a rule for tigris_delete_object: 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 Tigris. Nothing to install.
tigris_delete_object 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 tigris_delete_object 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 tigris_delete_object. 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.
tigris_delete_object is provided by the Tigris MCP server (@tigrisdata/tigris-mcp-server). 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 →