Execute SQL query on Supabase
AI agents invoke supabase.sql to trigger actions in MCP Fullstack. 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 inherently an Execute-category tool because it runs code against a database whose effects depend on the query arguments. However, this warrants critical severity because: (1) SQL queries can be destructive (DROP TABLE, DELETE), (2) can exfiltrate sensitive data (SELECT from any table), (3) can modify data (UPDATE, INSERT), and (4) an AI agent with unsanitized query construction could cause severe…
From the tool's definition Tool name 'supabase.sql' and description 'Execute SQL query on Supabase' indicate arbitrary SQL query execution capabilities.
Attacks that exploit this kind of access
Execute SQL query on Supabase. It is categorised as a Execute tool in the MCP Fullstack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for supabase.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 MCP Fullstack. Nothing to install.
supabase.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.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.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.sql is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →