We recently released Neon’s remote MCP server. In this post, we’ll dive deep into how we implemented Neon’s remote MCP server. We’ll explore using Server Sent Events (SSE) for communication and integrating OAuth 2.1 for authentication. So let’s dive in. Note If you’d rather watch...

We often take Postgres features like JSONB, Row Level Security (RLS), and Point In Time Recovery (PITR) for granted. Yet, these powerful features we know and love weren’t always available; they’re the result of over 30 years of dedicated development and almost 61000 Git commits. ...

At Neon, we like to be on top of things, especially when it comes to AI. We first announced our MCP server back on December 3rd, 2024. That was a long time before MCP really took off, and we’ve been iterating on our MCP server’s capabilities ever since. You can read more about ou...

Vercel’s v0 recently introduced integrations for Neon, Supabase, and Upstash. With these integrations, you can easily add persistent storage and deploy full stack applications in minutes. However, detailed prompting is essential to guide v0 effectively. Since its initial launch, ...

Agents can be implemented using various GenAI (Generative AI) frameworks, including LangChain, LangGraph, LlamaIndex, and Semantic Kernel. All these frameworks support using Neon. Implementing AI driven functions or tools calling required hundreds of lines of code—now, it takes j...

Since the release of GitHub Copilot, AI integration in IDEs has evolved dramatically. Now, two IDEs are being talked about more than any other Windsurf and Cursor. Both tools are forks of VSCode, offer a similar set of features, and use Anthropic’s Claude model under the hood. I ...

In this blog post, I’ll share my experience of vibe coding as I explore AI driven synthetic data generation, the tests I ran, and the challenges I faced along the way. What is vibe coding? Vibe coding is all about skipping the boilerplate and getting straight to the good stuff. I...

The Model Context Protocol (MCP) has been rapidly gaining traction, going viral on social media over the past two weeks. The community has already built dozens of MCP servers across a wide spectrum of domains, extending LLM capabilities with external tools, services, and data sou...

Making AI Work for Your Data AI agents are becoming active participants in data management. Nowadays instead of writing SQL queries, you can simply ask and chat with your data “Show me all shipments currently in transit.” Or even better, AI agents can act on your data “Create a n...

When you are building chat applications for internal teams or customer support, you need to isolate data to meet data residency and compliance requirements. Also, you want to chat with internal documents or APIs securely and safely. You can’t rely on public AI services like ChatG...