Azure / Azure/azure-sdk-for-python

Neon Serverless Postgres Knowledge tool for Azure AI Agent service using Azure AI Project

Open
#40,391 3 comments 0 reactions 1 assignee Claimed by @dargilco View on GitHub
AI Agents Client customer-reported feature-request needs-team-attention Service Attention
Dominant language
Python
Stars
5.6k
Forks
3.4k
Avg merge
2d 2h
Merged PRs (30d)
202

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](https://neon.tech/) 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.

Image
Image

- 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

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.