Delete a secret immediately.
AI agents call burn_secret to permanently remove resources in Sirr MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of secrets is irreversible and cannot be undone. This falls into the Destructive category as the most severe classification. Immediate deletion of secrets could eliminate critical credentials, API keys, or other sensitive data permanently, creating a critical blast radius if misused by an agent (e.g., deleting production secrets by mistake).
From the tool's definition Tool name 'burn_secret' with description 'Delete a secret immediately.' indicates irreversible deletion. The server description confirms it supports 'deleting secrets', and this tool performs that operation without recovery options.
Attacks that exploit this kind of access
Delete a secret immediately. It is categorised as a Destructive tool in the Sirr MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sirr MCP Server MCP server in PolicyLayer and add a rule for burn_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 Sirr MCP Server. Nothing to install.
burn_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 burn_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 burn_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.
burn_secret is provided by the Sirr MCP Server MCP server (sirrlock/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 →