supabase_execute_sql
Run a SQL statement against a Supabase project's database via the Management API. Destructive statements require confirm: true.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/supabase-execute-sql.md
What supabase_execute_sql does on UnClick
AI agents invoke supabase_execute_sql to trigger actions in UnClick. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
sql | string | Yes | The SQL to run. |
api_key | string | — | Legacy token alias. |
confirm | boolean | — | Set true to allow a destructive statement the guard would block. |
project_ref | string | Yes | Supabase project ref (the xxxx in xxxx.supabase.co). |
access_token | string | — | Optional Supabase access token. Omit to use the connected login. |
Parameters from the server's own tool schema.
Why supabase_execute_sql is rated High
This tool executes arbitrary SQL statements, which falls under Execute rather than Destructive, because: (1) the primary purpose is to run SQL queries whose effects depend on the agent's argument; (2) destructive operations (DROP, DELETE) are gated by a confirmation requirement; (3) the unconfirmed execution of SELECT, INSERT, UPDATE, and other non-destructive statements constitutes arbitrary code execution against…
From the tool's definition Tool description states 'Run a SQL statement against a Supabase project's database via the Management API.
Risk signalsAccepts freeform code/query input (sql) · Handles credentials or secrets (access_token)
Attacks that exploit this kind of access
The rule that runs supabase_execute_sql safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For supabase_execute_sql, this is the rule to start with:
supabase_execute_sql 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.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every supabase_execute_sql call is checked against it from then on.
Questions about supabase_execute_sql
Run a SQL statement against a Supabase project's database via the Management API. Destructive statements require confirm: true. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
supabase_execute_sql accepts 5 parameters: sql, api_key, confirm, project_ref, access_token. Required: sql, project_ref. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick 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 UnClick. 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 UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
Across the catalogue