Delete a blob from Walrus storage
AI agents call delete_blob to permanently remove resources in Walrus MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from decentralized storage and cannot be undone. The operation results in irreversible loss of the specified blob, which constitutes a destructive action. While the blast radius is limited to a single blob at a time (mitigating critical severity), the irreversible nature of deletion and potential for accidental loss of important data warrants 'high' severity.
From the tool's definition Tool name is 'delete_blob' with description 'Delete a blob from Walrus storage'. The verb 'delete' directly indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a blob from Walrus storage. It is categorised as a Destructive tool in the Walrus MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Walrus MCP Server MCP server in PolicyLayer and add a rule for delete_blob: 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 Walrus MCP Server. Nothing to install.
delete_blob 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_blob 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_blob. 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_blob is provided by the Walrus MCP Server MCP server (motion-labs-sui/walrus-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 →