Execute a PostgreSQL function/stored procedure
AI agents invoke supabase_rpc to trigger actions in Supabase MCP Server. 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.
This tool allows execution of PostgreSQL functions and stored procedures with effects that depend entirely on what function is called and its arguments. While the tool itself doesn't inherently delete or move money, it can trigger arbitrary database logic.
From the tool's definition Tool description states 'Execute a PostgreSQL function/stored procedure' - the verb 'Execute' combined with the ability to run arbitrary PostgreSQL functions indicates code execution capabilities.
Attacks that exploit this kind of access
Execute a PostgreSQL function/stored procedure. It is categorised as a Execute tool in the Supabase MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Supabase MCP Server MCP server in PolicyLayer and add a rule for supabase_rpc: 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 MCP Server. Nothing to install.
supabase_rpc 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_rpc 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_rpc. 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_rpc is provided by the Supabase MCP Server MCP server (sweir1/supabase-mcp-server). 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 →