# Best Postgres for AI apps (/docs/postgres/best-postgres-for-ai-apps)

> For the complete Prisma documentation index, see [llms.txt](https://www.prisma.io/docs/llms.txt). A markdown version of any docs page is available by appending `.md` to its URL.

Why Prisma Postgres works well for AI and LLM workloads: built-in pooling, edge connectivity, pgvector, and MCP support.

Location: Postgres > Best Postgres for AI apps

AI apps have a different database profile than traditional web apps. Requests burst unpredictably, inference runs at the edge, and agents increasingly need direct database access. Most managed Postgres services weren't designed with those patterns in mind.

## Built-in connection pooling [#built-in-connection-pooling]

Serverless inference endpoints open a new database connection per invocation. At any meaningful load, that exhausts your Postgres connection limit fast. Prisma Postgres includes connection pooling by default, so there is no PgBouncer to configure and no sidecar to run. Your connection string already points to the pooler.

## Edge-native connectivity [#edge-native-connectivity]

Standard Postgres TCP drivers don't work in Cloudflare Workers, Vercel's Edge runtime, or Deno Deploy. Prisma Postgres ships `@prisma/ppg`, a serverless driver that connects over HTTP.

See [Serverless driver](https://www.prisma.io/docs/postgres/database/serverless-driver) for setup.

## pgvector for embeddings [#pgvector-for-embeddings]

Prisma Postgres supports the `pgvector` extension for storing and querying vector embeddings natively in Postgres. You can keep your embeddings alongside your application data without a separate vector store.

See [Postgres extensions](https://www.prisma.io/docs/postgres/database/postgres-extensions) for how to enable it.

## MCP server for agent workflows [#mcp-server-for-agent-workflows]

AI agents (Claude, Cursor, or custom) can connect to Prisma Postgres via the Prisma MCP server to introspect schemas, run queries, apply migrations, and manage environments, without raw SQL access.

See [Prisma MCP server](https://www.prisma.io/docs/ai/tools/mcp-server) for setup.

## At a glance [#at-a-glance]

|                                 | Prisma Postgres           | Neon                            | Supabase                        |
| ------------------------------- | ------------------------- | ------------------------------- | ------------------------------- |
| **Built-in connection pooling** | Yes, included by default  | Yes, PgBouncer-compatible       | Yes, Supavisor pooler           |
| **Serverless / edge driver**    | Yes, `@prisma/ppg`        | Yes, `@neondatabase/serverless` | Partial, requires configuration |
| **pgvector support**            | Yes                       | Yes                             | Yes                             |
| **MCP server**                  | Yes, official first-party | Yes, Neon MCP server            | Yes, Supabase MCP server        |
| **Database branching**          | No                        | Yes                             | Limited                         |
| **Free tier**                   | Yes                       | Yes                             | Yes                             |

## Get started [#get-started]

  

#### bun

```bash
bun create prisma@latest
```

#### pnpm

```bash
pnpm create prisma@latest
```

#### yarn

```bash
yarn create prisma@latest
```

#### npm

```bash
npm create prisma@latest
```

Or provision from the [Prisma Console](https://console.prisma.io/?utm_source=docs\&utm_medium=content\&utm_content=postgres) and grab your connection string.

* [Connect to Prisma Postgres](https://www.prisma.io/docs/postgres/database/connecting-to-your-database)
* [Use the serverless driver at the edge](https://www.prisma.io/docs/postgres/database/serverless-driver)
* [Enable pgvector](https://www.prisma.io/docs/postgres/database/postgres-extensions)
* [Set up the Prisma MCP server](https://www.prisma.io/docs/ai/tools/mcp-server)

## Related pages

- [`create-db`](https://www.prisma.io/docs/postgres/npx-create-db): Create a temporary Prisma Postgres database with one command and no sign-up, for prototypes, tests and coding agents. Claim it with a Prisma account to keep it.
- [`Database`](https://www.prisma.io/docs/postgres/database): Overview of Prisma Postgres database operations, connections, pooling, backups, and query analysis.
- [`Error reference`](https://www.prisma.io/docs/postgres/error-reference): Error reference documentation for Prisma Postgres
- [`Migrate a local Postgres database to the cloud (Prisma Postgres)`](https://www.prisma.io/docs/postgres/import-from-existing-database): Move a local or hosted PostgreSQL database to Prisma Postgres in three steps: create the database, pg_dump, pg_restore.
- [`Migrate from Early Access`](https://www.prisma.io/docs/postgres/migrate-from-ea-to-ga): Move your Prisma Postgres Early Access database to a new PostgreSQL 17 database with dump and restore.