AI agents invoke query 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.
Executing arbitrary SQL can perform any operation including SELECT, INSERT, UPDATE, DELETE, DROP, or TRUNCATE. Since it can span Read through Destructive categories, the most severe applicable category is Execute (or potentially Destructive if DROP/DELETE are permitted).
From the tool's definition 'Execute a SQL query' — the tool runs arbitrary SQL against a PostgreSQL database
Documented attack patterns abuse exactly the kind of access query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Supabase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query:
{
"version": "1",
"default": "deny",
"tools": {
"query": {
"limits": [
{
"counter": "query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a SQL query. 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 query: 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.
query 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 query 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 query. 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.
query is provided by the Supabase MCP Server MCP server (quegenx/supabase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Supabase MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Supabase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.