Sep 25, 2026

How to Build an App on Base44 with a Production-Ready Aiven Database

With Base44 and Aiven's managed PostgreSQL, you can go from idea to production-ready app in minutes - with your data living in your own cloud infrastructure.

Yonatan Dvir |

RSS Feed

Software Engineer

This guide shows you how to connect Base44 to Aiven PostgreSQL using the MCP, enabling you to provision and manage production-ready databases directly from within Base44.

Base44 is fast at the part that used to take a week. Describe an application, and you have a working interface in minutes.

Base44's built-in Cloud backend, enabled by default, is a reasonable place to start. But it doesn't put your data in an account you already own, in the cloud and region you picked, next to the rest of your data platform.

That's the gap this post closes. Connect the Aiven MCP to Base44 once, and its agent can operate on your Aiven account: list projects, provision PostgreSQL, create tables, seed data, and deploy to Aiven Runtime. You specify the product; the agent handles the infrastructure.

We recorded a full session. This post walks through what happened and which parts are worth copying.

What the Aiven MCP does

The Model Context Protocol is a standard interface for AI agents calling external tools. The Aiven MCP exposes the Aiven platform through that interface: projects, service plans, clouds, provisioning, PostgreSQL reads and writes, and application deploys.

Because it implements a standard, it is not specific to Base44. It works the same way from Claude, Cursor and VS Code Copilot, which we covered in Aiven MCP: Build on Aiven from Your AI Agent.

Connecting Base44 to Aiven

One prerequisite. An organization admin enables MCP access in the Aiven Console under Admin settings > Authentication > Allow MCP connection. Without it, MCP clients cannot connect for anyone in the organization.

In Base44, open Settings, select MCP Connections, Click Add Custom MCP and add the Aiven MCP URL:

Loading code...

Authentication uses OAuth 2.0 with PKCE. Base44 redirects to Aiven for authorization, so there are no API keys to move between systems. Base44 then lists the individual Aiven tools the connector exposes.

MCP connectors in Base44 are build-time tools: they give it context and capability while it works, not a runtime connection for the deployed application. That distinction matters later, when the app needs its own credentials.

By default the Aiven MCP redacts service connection information, so the agent never receives your database URI, password or certificates. It can still create tables and run queries, because those calls go through Aiven MCP tools rather than a direct database connection.

The connector can be narrowed further. Setting services_scope=pg restricts it to PostgreSQL tools; AIVEN_READ_ONLY=true produces a connection that can inspect but not modify; AIVEN_WRITE_ALLOWLIST re-enables named write tools inside a read-only connection. The shared responsibility model is worth reading before pointing an agent at any project that matters.

Building Your First App

With the MCP connected, you can start building. Simply describe your application to Base44, and its AI agent will:
  1. Query Your Aiven Account: The agent retrieves your available projects, service plans, and cloud regions directly from Aiven.
  2. Provision Infrastructure: Based on your requirements, the agent will select the appropriate Aiven project, choose the right service plan (from free tier to production), pick the optimal cloud and region, and provision an Aiven for PostgreSQL service.
  3. Set Up Your Database: Once the service is running, the agent can create tables based on your app's data model, seed the database with sample data, and run queries to verify the setup.
  4. Build Your App: The agent builds your Base44 application connected to your Aiven database, with the data layer ready to go.
The Aiven MCP is designed with security in mind:
  1. Token-based authentication: Your Aiven token is stored securely in Base44 and used only for MCP requests
  2. Scope control: Use read-only mode or specific scopes to limit what the agent can do
  3. Your infrastructure: The database lives in your Aiven account - you own and control the data

Reproducing this setup

  1. Ask an organization admin to enable Allow MCP connection under Admin settings > Authentication in Aiven Console.
  2. In Base44, add a custom MCP connector pointing at https://mcp.aiven.live/mcp and complete the OAuth flow.
  3. Describe your application and let Base44 provision Aiven for PostgreSQL. The free tier with 1 CPU and 1 GB RAM is sufficient for the provisioning and data-layer steps. The deploy step requires a paid plan, because the free tier does not support service integrations and integrations are how credentials reach the deployed application.
  4. When the app needs to connect, copy the service URI from the Aiven Console and add it to Base44 as a secret.
  5. Instruct the agent to deploy, and select the Aiven service integration when asked about credentials.

Get started

If you are new to Aiven, sign up for free plans and trial credits. The Aiven MCP is open source and available on GitHub.

Frequently asked questions

An MCP server exposes a set of tools that an AI agent can call. A custom server is one you add yourself rather than selecting from a built-in list. https://mcp.aiven.live/mcp is the Aiven MCP. Adding it to Base44 allows the agent to list projects, provision services, run PostgreSQL queries and deploy applications on your Aiven account.

There is a free tier consisting of one single-node service per organization, with 1 CPU, 1 GB RAM and 1 GB of storage, including backups, metrics and logs. It does not support VPCs, static IPs, connection pooling or service integrations, and limits max_connections to 20. It is suitable for trying this workflow. The deploy step requires a paid plan such as startup-4, which provides 1 CPU, 4 GB RAM and 80 GB of storage.

Yes. The same Aiven MCP exposes Apache Kafka, Aiven Runtime and other Aiven services alongside PostgreSQL. The services_scope parameter controls what the agent can see, accepting pg, kafka, application, integrations, core or all.