supabase_execute_sql
AI agents invoke supabase_execute_sql to trigger actions in Integrations MCP. 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.
SQL execution is the Execute category by definition—it runs code whose effects depend entirely on the SQL argument provided. With an empty description, we cannot rule out destructive operations (DROP, DELETE, TRUNCATE) or data exfiltration. An AI agent given this tool without safeguards could easily drop tables, corrupt data, or extract sensitive information.
From the tool's definition Tool name 'supabase_execute_sql' explicitly indicates execution of SQL queries against a Supabase database. The 'execute_sql' verb combined with a database context means arbitrary SQL execution capability.
Attacks that exploit this kind of access
supabase_execute_sql. It is categorised as a Execute tool in the Integrations MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Integrations MCP server in PolicyLayer and add a rule for supabase_execute_sql: 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_execute_sql 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_execute_sql 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_execute_sql. 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_execute_sql 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 →