Delete a secret
AI agents call secrets.delete to permanently remove resources in MCP Fullstack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting secrets is an irreversible operation that destroys authentication credentials, API keys, or other sensitive data. If an AI agent misuses this tool, it could permanently remove access credentials needed for application functionality, cause service outages, or lock out legitimate users. This is the highest-severity category due to the permanent nature of the action and potential for cascading system failures.
From the tool's definition Tool name is 'secrets.delete' with description 'Delete a secret'. The verb 'delete' combined with the 'Destructive' category definition (irreversibly deletes data, actions that cannot be undone) directly matches.
Attacks that exploit this kind of access
Delete a secret. It is categorised as a Destructive tool in the MCP Fullstack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for secrets.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 MCP Fullstack. Nothing to install.
secrets.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 secrets.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 secrets.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.
secrets.delete is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →