claimable-postgres

FIRST: Use the parent neon skill for a Neon overview, getting started with Neon, Neon development best practices, and more.

If the neon skill is not installed, fetch it from https://neon.com/docs/ai/skills/neon/SKILL.md or install it with:

npx skills add neondatabase/agent-skills --skill neon

Claimable Postgres

Instant Postgres databases for local development, demos, prototyping, and test environments. No account required. Databases expire after 72 hours unless claimed to a Neon account.

Quick Start

curl -s -X POST "https://neon.new/api/v1/database" \
  -H "Content-Type: application/json" \
  -d '{"ref": "agent-skills"}'

Parse connection_string and claim_url from the JSON response. Write connection_string to the project's .env as DATABASE_URL.

For other methods (CLI, SDK, Vite plugin), see Which Method? below.

Which Method?

• REST API: Returns structured JSON. No runtime dependency beyond curl. Preferred when the agent needs predictable output and error handling.
• CLI (npx neon-new@latest --yes): Provisions and writes .env in one command. Convenient when Node.js is available and the user wants a simple setup.
• SDK (neon-new/sdk): Scripts or programmatic provisioning in Node.js.
• Vite plugin (vite-plugin-neon-new): Auto-provisions on vite dev if DATABASE_URL is missing. Use when the user has a Vite project.
• Browser: User cannot run CLI or API. Direct to https://neon.new.

Auto-provisioning

If the agent needs a database to fulfill a task (e.g. "build me a todo app with a real database") and the user has not provided a connection string, provision one via the API and inform the user. Include the claim URL so they can keep it.

Agent Workflow

API path

1. Confirm intent: If the request is ambiguous, confirm the user wants a temporary, no-signup database. Skip this if they explicitly asked for a quick or temporary database.
2. Provision: POST to https://neon.new/api/v1/database with {"ref": "agent-skills"}.
3. Parse response: Extract connection_string, claim_url, and expires_at from the JSON response.
4. Write .env: Write DATABASE_URL=<connection_string> to the project's .env (or the user's preferred file and key). Do not overwrite an existing key without confirmation.
5. Seed (if needed): If the user has a seed SQL file, run it against the new database:

   psql "$DATABASE_URL" -f seed.sql
   

6. Report: Cover every item in the Output Checklist.
7. Optional: Offer a quick connection test (e.g. SELECT 1).