Delete an auth user from the Supabase project.
AI agents call supabase_delete_user to permanently remove resources in Integrations MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes user authentication data from a Supabase project, which cannot be undone and represents loss of a user account. This is a destructive operation with significant blast radius if triggered incorrectly by an AI agent (e.g., deleting the wrong user). While not financial in nature, destructive operations rank above execute/write/read in severity.
From the tool's definition Tool name explicitly contains 'delete' and description states 'Delete an auth user from the Supabase project' — this is an irreversible removal of user authentication records.
Attacks that exploit this kind of access
Delete an auth user from the Supabase project. It is categorised as a Destructive tool in the Integrations MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Integrations MCP server in PolicyLayer and add a rule for supabase_delete_user: 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 Integrations MCP. Nothing to install.
supabase_delete_user 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 supabase_delete_user 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 supabase_delete_user. 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.
supabase_delete_user is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →