Skip to main content

AI tools for working with databases

To work with a database from an AI agent, the Supabase MCP server lets it list tables, draft and apply migrations, run SQL, and read advisors against a real Postgres schema — and the Supabase agent skills front-load the RLS and migration guidance that prevents costly mistakes. Always point schema-changing work at a staging project first.

Supabase MCP server + Supabase agent skills.

Curated by Joaquin FuentesLast updated: June 14, 2026

Recommended resources

Supabase Agent Skills

Database, migration, and security guidance for agents.

Supabase's installable agent skills add critical local-development and security guidance for working against a Supabase project — installed with a single `npx skills add` command.

Claude CodeFreeOfficialIntermediate
skillsdatabasesecurity
npx skills add supabase/agent-skills
When to use & gotchas

When to use Install it before letting an agent near a Supabase project — it front-loads the RLS and migration guidance that prevents the expensive mistakes.

Supabase MCP Server

Query, migrate, and inspect your Postgres from the agent.

Connect an agent to a Supabase project to list tables, apply migrations, run SQL, and read advisors — a fast loop for schema work when paired with disciplined review.

Any toolFreeOfficialAdvanced
mcpdatabasepostgresmigrations
When to use & gotchas

When to use Use it for inspect-heavy work — listing tables, reading advisors, drafting migrations — where seeing the real schema beats guessing from code.

Gotcha `apply_migration` writes straight to the target project. Always run schema changes against a staging project first and gate every apply behind your own approval.

Frequently asked questions

Can an AI agent run database migrations?

Yes, via the Supabase MCP server — but apply_migration writes straight to the target project, so run migrations against staging first and gate every apply behind your own approval.

How do I keep an agent from breaking my data?

Install the Supabase agent skills (RLS + migration guidance), work against a staging project, and review every SQL change before it runs on production.

← Back to all resources