supabase
AI agents invoke supabase to trigger actions in MCP Lite Wrappers. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Supabase is a full-featured backend platform supporting database queries, mutations, storage, auth, and edge functions. A wrapper consolidating 'multiple tools' with 'full functionality' could read, write, execute SQL, or destructively delete data. Without a description, the worst-case (Execute/Destructive) must be assumed.
From the tool's definition Tool name 'supabase' with empty description; server description states it wraps Supabase tools with 'full functionality'
Attacks that exploit this kind of access
supabase. It is categorised as a Execute tool in the MCP Lite Wrappers MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Lite Wrappers MCP server in PolicyLayer and add a rule for supabase: 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 MCP Lite Wrappers. Nothing to install.
supabase is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the supabase 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. 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 is provided by the MCP Lite Wrappers MCP server (sbraind/mcp-lite-wrappers). 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 →