Delete a single object. (Refused on read-only / production add-ons.)
AI agents call delete_object to permanently remove resources in Rustfs — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently and irreversibly removes data from S3-compatible object storage. There is no undo mechanism; deleted objects cannot be recovered. While the blast radius depends on what objects are targeted, the capability itself is inherently destructive. It does not move money (Financial) or merely modify data reversibly (Write).
From the tool's definition Tool name is 'delete_object' and description states 'Delete a single object.' The verb 'delete' and explicit statement of object deletion indicate irreversible removal of data.
Attacks that exploit this kind of access
Delete a single object. (Refused on read-only / production add-ons.). It is categorised as a Destructive tool in the Rustfs MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rustfs MCP server in PolicyLayer and add a rule for 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 Rustfs. Nothing to install.
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 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 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.
delete_object is provided by the Rustfs MCP server (stackblaze/rustfs-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 →