AI agents call delete_secret to permanently remove resources in Claude Secrets — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting secrets is a destructive action that permanently removes data from the encrypted token store. Even though it requires an allowlist, the capability to irreversibly remove secrets poses a high risk if misused by an AI agent, as secrets once deleted cannot be recovered. This is more severe than Write (reversible modification) and qualifies as Destructive.
From the tool's definition Tool name is 'delete_secret' and description states 'Delete a secret by name.' This is an irreversible deletion operation that cannot be undone.
Documented attack patterns abuse exactly the kind of access delete_secret gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Secrets, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_secret:
{
"version": "1",
"default": "deny",
"hide": [
"delete_secret"
]
}delete_secret disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a secret by name. Requires allowlist. It is categorised as a Destructive tool in the Claude Secrets MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Secrets MCP server in PolicyLayer and add a rule for delete_secret: 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 Claude Secrets. Nothing to install.
delete_secret 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_secret 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_secret. 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_secret is provided by the Claude Secrets MCP server (vaultry/claude-secrets). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Secrets, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Claude Secrets tools catalogued and risk-classified — across an index of 43,000+ MCP servers.