AI agents call delete_api_key to permanently remove resources in AnythingLLM MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting an API key is an irreversible destructive action that permanently removes access credentials. While not as severe as data deletion, it has significant blast radius: a mistaken deletion could revoke legitimate service access, break integrations, or lock users out of AnythingLLM functionality.
From the tool's definition Tool name explicitly states 'delete' combined with 'api_key'. Description confirms 'Delete an API key' - a permanent, irreversible action that removes authentication credentials.
Documented attack patterns abuse exactly the kind of access delete_api_key gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AnythingLLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_api_key:
{
"version": "1",
"default": "deny",
"hide": [
"delete_api_key"
]
} delete_api_key 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 an API key. It is categorised as a Destructive tool in the AnythingLLM MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AnythingLLM MCP Server MCP server in PolicyLayer and add a rule for delete_api_key: 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 AnythingLLM MCP Server. Nothing to install.
delete_api_key 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_api_key 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_api_key. 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_api_key is provided by the AnythingLLM MCP Server MCP server (raqueljezweb/anythingllm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AnythingLLM MCP Server, 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.
38 AnythingLLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.