How to Use the Neon MCP in Vercel AI SDK

Q: How do I connect the Neon MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient. Pass your Vinkius HTTP URL into the transport configuration, then call mcpClient.tools() to expose the Neon commands to your model.

Q: Can Vercel AI SDK stream Neon database creation results?

Yes. When the agent calls createdatabase, you pass the tool call through streamText. The React frontend receives the database metadata the second the Neon API responds.

Q: How does Neon handle branching through the Vercel AI SDK?

The agent uses createbranch to clone environments instantly using copy-on-write. You do not wait for data to copy, meaning the UI updates immediately with the new branch details.

Q: Do I need to manage connection states manually?

No. Always call mcpClient.close() when your Edge Function finishes executing. The SDK handles the transport layer while Neon manages the serverless Postgres connections.

Build user-facing database provisioning tools with Vercel AI SDK. Stream live Neon Postgres infrastructure directly into your frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon MCP to Vercel AI SDK

Create your Vinkius account to connect Neon 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 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Neon MCP Server Operations Live

`create_project` and `create_branch` let your AI client provision instant Postgres environments. You plug this MCP Server into your Vercel AI SDK setup, and suddenly your users can spin up databases right from a chat interface. The model executes the call, and the resulting connection strings stream straight into your Next.js frontend without loading spinners. Your users never wait. You call `mcpClient.tools()` and pass it to `streamText`. As the AI triggers `get_connection_uri` to fetch the host and password, the UI updates instantly. Edge compatibility means you run this close to your users, keeping database provisioning latency at absolute minimums.

Render Interactive Database Dashboards

`list_projects` and `list_branches` pull live serverless Postgres states straight into your Svelte or Vue application. Instead of static text, your AI agent fetches the active compute endpoints and databases. You map those tool results into React components, showing developers exactly what branches they have available. Building internal developer portals gets fast. When a user asks for a test environment, the model triggers `create_branch` with a specific parent ID. The moment Neon finishes the zero-copy clone, the new branch data flows back through the AI SDK, rendering the fresh connection details on screen immediately.

Manage Roles and Compute Endpoints

`create_endpoint` and `create_role` handle the exact compute and access needs of your application. You expose these tools to your Vercel AI SDK agent, allowing users to request a read-only replica or generate a new set of credentials on the fly. The agent handles the parameters, passing the project ID and branch ID under the hood. You maintain total control over what gets exposed. Since Vercel AI SDK handles OAuth via `authProvider`, you ensure only authorized users trigger destructive actions like `delete_branch`. You give developers the power to manage their Postgres infrastructure through natural language, securely and in real time.

Setup guide

Set up Neon 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 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 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 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 MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and use `createMCPClient`. Pass your Vinkius HTTP URL into the transport configuration, then call `mcpClient.tools()` to expose the Neon commands to your model.

Yes. When the agent calls `create_database`, you pass the tool call through `streamText`. The React frontend receives the database metadata the second the Neon API responds.

The agent uses `create_branch` to clone environments instantly using copy-on-write. You do not wait for data to copy, meaning the UI updates immediately with the new branch details.

No. Always call `mcpClient.close()` when your Edge Function finishes executing. The SDK handles the transport layer while Neon manages the serverless Postgres connections.

This tool interacts directly with PostgreSQL connection URIs, passwords, and role metadata via `get_connection_uri`. Vinkius runs the server inside an ephemeral V8 Isolate Sandbox, ensuring your database secrets exist only during the exact moment of execution and disappear entirely once the AI request completes.

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