Scan a Supabase project for security issues: RLS gaps, exposed SECURITY DEFINER functions, public buckets, default-privilege leaks, and unsafe auth config. Returns findings JSON. Caches result for use by apply_fix tools.
AI agents call audit_project to retrieve information from Supabase Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only audit/scan of a Supabase project, identifying security misconfigurations and returning findings as JSON. It does not modify, delete, or execute anything — it only reads configuration and state.
From the tool's definition Scan a Supabase project for security issues... Returns findings JSON. Caches result for use by apply_fix tools.
Attacks that exploit this kind of access
Scan a Supabase project for security issues: RLS gaps, exposed SECURITY DEFINER functions, public buckets, default-privilege leaks, and unsafe auth config. Returns findings JSON. Caches result for use by apply_fix tools. It is categorised as a Read tool in the Supabase Security MCP Server, which means it retrieves data without modifying state.
Register the Supabase Security MCP server in PolicyLayer and add a rule for audit_project: 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 Supabase Security. Nothing to install.
audit_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the audit_project 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 audit_project. 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.
audit_project is provided by the Supabase Security MCP server (perufitlife/supabase-security-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 →