AI agents call awx_credential_delete to permanently remove resources in Pypi:awx — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes credentials from AWX, which are sensitive authentication objects. Deletion cannot be undone and has severe consequences: losing access to infrastructure, breaking automation workflows, and potentially exposing systems if credential recovery is not available. An AI agent misusing this could permanently remove credentials needed for critical operations.
From the tool's definition Tool name 'awx_credential_delete' explicitly performs deletion of AWX credentials. The verb 'delete' indicates irreversible removal of data.
Documented attack patterns abuse exactly the kind of access awx_credential_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pypi:awx, and nothing reaches the server without passing your rules. This is the rule we recommend for awx_credential_delete:
{
"version": "1",
"default": "deny",
"hide": [
"awx_credential_delete"
]
} awx_credential_delete 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 AWX credential. It is categorised as a Destructive tool in the Pypi:awx MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pypi:awx MCP server in PolicyLayer and add a rule for awx_credential_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 Pypi:awx. Nothing to install.
awx_credential_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 awx_credential_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 awx_credential_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.
awx_credential_delete is provided by the Pypi:awx MCP server (SurgeX-Labs/awx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pypi:awx, 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.
50 Pypi:awx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.