delete_guardrail
Delete a guardrail by id or slug. This is irreversible and removes the check from any configs that reference it, so review dependent configs first.
This record as markdown: /tools/codeswhat-portkey-admin-mcp/delete-guardrail.md
What delete_guardrail does on Portkey Admin
AI agents call delete_guardrail to permanently remove resources in Portkey Admin, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why delete_guardrail is rated Critical
The tool permanently deletes data (a guardrail) without the ability to restore it. This fits the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone'. While not financial and not a cascade delete affecting the entire system, it has clear downstream effects on dependent configurations, making it high severity.
From the tool's definition Tool description explicitly states 'Delete a guardrail' and 'This is irreversible'. The description emphasizes the action cannot be undone and removes the check from configs that reference it.
Attacks that exploit this kind of access
The rule that runs delete_guardrail safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Portkey Admin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delete_guardrail, this is the rule to start with:
delete_guardrail is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Portkey Admin, apply this rule, and every delete_guardrail call is checked against it from then on.
Questions about delete_guardrail
Delete a guardrail by id or slug. This is irreversible and removes the check from any configs that reference it, so review dependent configs first. It is categorised as a Destructive tool in the Portkey Admin MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for delete_guardrail: 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 Portkey Admin. Nothing to install.
delete_guardrail 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_guardrail 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_guardrail. 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_guardrail is provided by the Portkey Admin MCP server (codeswhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Portkey Admin, and thousands of servers like it.
Across the catalogue