How to Use the Neon (Serverless PostgreSQL) MCP in Vercel AI SDK

Q: How do I handle Neon (Serverless PostgreSQL) credentials in Vercel AI SDK edge functions?

Pass your Vinkius token to createMCPClient inside your Next.js edge route. The Vercel AI SDK communicates securely with the MCP Server, keeping your Neon database credentials hidden from the browser.

Q: Can the Vercel AI SDK stream the progress of Neon (Serverless PostgreSQL) branch creation?

Yes. Using streamText and this MCP Server, the model calls createbranch and streams the resulting branch details directly to your React UI. The user sees the copy-on-write clone become active in seconds.

Q: How does the Vercel AI SDK handle parallel calls to listendpoints?

The SDK executes the listendpoints tool through the MCP client to fetch active connection strings. It automatically handles the JSON payload and feeds the routing endpoints directly to your UI components.

Q: Do I need to clean up connections after calling deleteproject?

No. When the model invokes deleteproject, the serverless database severs all active connections. Make sure to call mcpClient.close() in your TypeScript code to clean up the SDK client itself.

Spin up zero-copy database branches and stream live schema updates directly to your React or Next.js UI using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon (Serverless PostgreSQL) MCP to Vercel AI SDK

Create your Vinkius account to connect Neon (Serverless PostgreSQL) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Neon (Serverless PostgreSQL) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live branch creation to your Vercel AI SDK UI

Look, `create_branch` runs instantly to clone your production database, and this MCP Server streams the entire lifecycle directly to your Vercel AI SDK frontend. Your users watch the database duplicate in real-time on their screens instead of staring at some blank loading spinner. The client handles the connection via `createMCPClient` and feeds the output directly into `streamText`. That means you render live status bars for database isolation tasks without writing custom API polling routes.

Live schema discovery inside React components

`list_databases` exposes the internal SQL schemas on any active branch, letting your Vercel AI SDK application dynamically render schema dropdowns for your users. The raw database structure flows straight from the Neon API into your UI components as your agent gets the data. By passing the tool list to `generateText`, your interface updates dynamically based on active branches. You don't need to hardcode database names or maintain complex sync states in your frontend code.

Instant environment tear-downs from user interactions

`delete_project` wipes out entire database environments and severs active connections, and you trigger this directly from user-facing buttons using the Vercel AI SDK. It gives your users total control over their serverless workspaces with instant visual feedback as the physical NVMe storage blocks evaporate. Register the tool in your edge function and let the SDK handle the lifecycle. This keeps your database cleanups fast and ensures your frontend stays perfectly synced with your infrastructure state.

Setup guide

Set up Neon (Serverless PostgreSQL) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Neon (Serverless PostgreSQL) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Neon (Serverless PostgreSQL) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Neon. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Neon (Serverless PostgreSQL) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Neon (Serverless PostgreSQL) MCP in Vercel AI SDK

Pass your Vinkius token to `createMCPClient` inside your Next.js edge route. The Vercel AI SDK communicates securely with the MCP Server, keeping your Neon database credentials hidden from the browser.

Yes. Using `streamText` and this MCP Server, the model calls `create_branch` and streams the resulting branch details directly to your React UI. The user sees the copy-on-write clone become active in seconds.

The SDK executes the `list_endpoints` tool through the MCP client to fetch active connection strings. It automatically handles the JSON payload and feeds the routing endpoints directly to your UI components.

No. When the model invokes `delete_project`, the serverless database severs all active connections. Make sure to call `mcpClient.close()` in your TypeScript code to clean up the SDK client itself.

Vinkius runs the server in an isolated V8 sandbox. This prevents the Vercel AI SDK from exposing raw connection strings or Postgres schemas directly to the client-side bundle, keeping your data access layers completely isolated.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript