Description
Is your feature request related to a problem? Please describe.
Right now, we don’t have an easy way to use Neon Serverless Postgres as a knowledge base in the Azure AI Agent service. This makes it harder to store and query structured data directly from an AI agent, especially when working in a no-code setup using Azure AI Foundry.
Describe the solution you'd like
We would like to add support for Neon Serverless Postgres as a knowledge tool in the Azure AI Agent service. This should work with the Azure AI Project SDK and be available as a built-in no-code integration inside Azure AI Foundry. Neon is an official Microsoft partner and has a native integration for Microsoft Azure, so this would make the setup seamless and efficient.
Describe alternatives you've considered
We’ve looked at other databases, but they often need more setup or don’t support serverless features well. Neon’s serverless model fits well with Azure AI Agent’s scalable and event-driven architecture.
Additional context
Having this integration will make it much easier for developers and non-developers to build intelligent agents that can interact with structured data. It would also help keep everything within the Microsoft ecosystem and reduce friction during setup.
Neon is a serverless Postgres that’s a great fit for AI agents because:
- Agents can create their own databases programmatically.
- Each agent can get a separate, isolated database—useful for stateful reasoning, memory, or long-term storage.
- Neon supports branching, which is perfect for experimentation or simulations.
- There’s no cost when databases are idle, which aligns well with how agents operate asynchronously or event-driven.
You can find more context here on our AI agent use case page:
👉 https://neon.tech/use-cases/ai-agents
Related repos:
Neon + MCP + Azure AI Agent Serivce integration: https://github.com/neondatabase-labs/mcp-neon-azure-ai-agent
Neon + Azure AI Agent Demo project: https://github.com/neondatabase-labs/neon-azure-ai-agent-demo