Delete a blob from Shelby storage.
AI agents call shelby_delete to permanently remove resources in Shelby — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes data from storage without possibility of recovery. This is a destructive operation that cannot be undone. While the blast radius is limited to files the tool is given permission to delete, the irreversible nature of deletion warrants 'high' severity. Confidence is high because the description explicitly states deletion, which is unambiguously destructive.
From the tool's definition Tool name 'shelby_delete' and description 'Delete a blob from Shelby storage' indicate irreversible removal of data stored on decentralized storage (Aptos).
Attacks that exploit this kind of access
Delete a blob from Shelby storage. It is categorised as a Destructive tool in the Shelby MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Shelby MCP server in PolicyLayer and add a rule for shelby_delete: 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 Shelby. Nothing to install.
shelby_delete 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 shelby_delete 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 shelby_delete. 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.
shelby_delete is provided by the Shelby MCP server (jasekeee/shelby-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 →