# AI Tools

Connect your AI coding agent to Supabase.

Supabase provides everything you need to connect an AI coding agent to your project: a live connection to your database and platform (MCP), portable instructions your agent can reuse (Agent Skills), a one-step bundle of both (Plugin), and copy-paste prompts for tools that don't support any of the above.

Note: See how these tools perform on real Supabase tasks in [Supabase Evals](/evals), our open-source benchmark for AI coding agents.

## Pick your agent

- **[Antigravity](/docs/guides/ai-tools/plugins):** Experience liftoff with the next-gen agent platform.
- **[Claude Code](/docs/guides/ai-tools/plugins):** Work with Claude directly in your codebase, from your terminal, IDE, and more.
- **[Codex](/docs/guides/ai-tools/plugins):** A lightweight coding agent that runs in your terminal.
- **[Cursor](/docs/guides/ai-tools/plugins):** Your coding agent for building ambitious software.
- **[Devin Desktop](/docs/guides/ai-tools/mcp):** The first agentic IDE. Tomorrow's editor, today.
- **[Factory](/docs/guides/ai-tools/mcp):** A self-improving system for your SDLC.
- **[fx](/docs/guides/ai-tools/mcp):** Connect using the Supabase MCP server or plugin.
- **[Gemini CLI](/docs/guides/ai-tools/plugins):** Build, debug & deploy with AI.
- **[GitHub Copilot](/docs/guides/ai-tools/plugins):** Your AI accelerator for every workflow, from the editor to the enterprise.
- **[Goose](/docs/guides/ai-tools/mcp):** Your native open source AI agent — desktop app, CLI, and API.
- **[Grok](/docs/guides/ai-tools/plugins):** Connect using the Supabase MCP server or plugin.
- **[Kimi Code](/docs/guides/ai-tools/plugins):** Engineered to drop into any dev workflow and get programming tasks done fast.
- **[Kiro](/docs/guides/ai-tools/mcp):** Move beyond AI coding to agentic engineering.
- **[omp](/docs/guides/ai-tools/plugins):** A coding agent with the IDE wired in.
- **[OpenCode](/docs/guides/ai-tools/mcp):** The open source AI coding agent.
- **[VS Code](/docs/guides/ai-tools/plugins):** The open source AI code editor — your home for multi-agent development.
- **[Warp](/docs/guides/ai-tools/mcp):** Connect using the Supabase MCP server or plugin.

## Key concepts

- **MCP (Model Context Protocol)**: a live connection between your agent and your actual Supabase project. Once connected, your agent can call tools to query data, run migrations, deploy Edge Functions, and more.
- **Agent Skills**: portable, on-demand instructions your agent loads when it needs Supabase- or Postgres-specific procedural knowledge. Skills don't require a live connection, and work across different agents.
- **Plugin**: a single install that bundles the MCP server and Agent Skills together for a specific agent.
- **Prompts**: static prompt files you copy into your project for agents that don't support MCP, plugins, or skills natively.

## Local projects for parallel agents

Agents that work in separate git worktrees or branches each need their own database. Otherwise migrations and seed data from one task affect another. With the experimental `supabase stack` commands turned on, `supabase start` gives each worktree or branch its own local Supabase project with its own ports and data. Agents that share one checkout and branch share a local project, so give each agent its own worktree. The commands also run without Docker on Linux and on macOS on Apple silicon, which covers agent sandboxes that have no container engine. See [Running multiple local projects](/docs/guides/local-development/running-multiple-local-projects) and [Docker and native runtimes](/docs/guides/local-development/docker-and-native-runtimes).

## Building AI into your app?

The tools above are for your development workflow. If you're building AI capabilities into your own product:

- **[Deploy MCP servers](/docs/guides/ai-tools/byo-mcp):** Host your own MCP server on Supabase Edge Functions so your users can connect their AI agents to your product
- **[Vectors / Embeddings](/docs/guides/ai):** Build semantic search, RAG pipelines, and other AI-powered features using pgvector