New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

execute_psql

Direct PostgreSQL access

SERVERSupabase MCP Server - Self-Hosted Edition SOURCEabdqum/supabase-mcp-selfhosted
High RISK CLASS
Category Execute
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/abdqum-supabase-mcp-selfhosted/execute-psql.md

What execute_psql does on Supabase MCP Server - Self-Hosted Edition

AI agents invoke execute_psql to trigger actions in Supabase MCP Server - Self-Hosted Edition. 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.

Why execute_psql is rated High

This tool provides direct access to execute arbitrary PostgreSQL queries and commands. While it could theoretically be used for Read operations, the capability to execute arbitrary SQL means it can also perform Write, Execute (procedural operations), and Destructive actions (DROP TABLE, DELETE, etc.).

From the tool's definition Tool name 'execute_psql' combined with description 'Direct PostgreSQL access' indicates execution of arbitrary PostgreSQL commands without apparent restrictions or guardrails.

Questions about execute_psql

What does the execute_psql tool do? +

Direct PostgreSQL access. It is categorised as a Execute tool in the Supabase MCP Server - Self-Hosted Edition MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_psql? +

Register the Supabase MCP Server - Self-Hosted Edition MCP server in PolicyLayer and add a rule for execute_psql: 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 - Self-Hosted Edition. Nothing to install.

What risk level is execute_psql? +

execute_psql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_psql? +

Yes. Add a rate_limit block to the execute_psql 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.

How do I block execute_psql completely? +

Set action: deny in the PolicyLayer policy for execute_psql. 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.

What MCP server provides execute_psql? +

execute_psql is provided by the Supabase MCP Server - Self-Hosted Edition MCP server (abdqum/supabase-mcp-selfhosted). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Supabase MCP Server - Self-Hosted Edition, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Supabase MCP Server - Self-Hosted Edition's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.