How to Use the Nile (PostgreSQL for Multi-Tenant Apps) MCP in Vercel AI SDK

Q: How do I connect Nile (PostgreSQL for Multi-Tenant Apps) to the Vercel AI SDK?

Install @ai-sdk/mcp. Use createMCPClient with your endpoint URL, then pass mcpClient.tools() into generateText or streamText. Always call mcpClient.close() when the session ends.

Q: How do I handle authentication for Nile (PostgreSQL for Multi-Tenant Apps) with Vercel AI SDK?

The MCP client supports an authProvider configuration. You pass your OAuth tokens or API keys there, and the connection handles the zero-trust handshake automatically.

Build React interfaces that provision isolated PostgreSQL instances in real time 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 Nile (PostgreSQL for Multi-Tenant Apps) MCP to Vercel AI SDK

Create your Vinkius account to connect Nile (PostgreSQL for Multi-Tenant Apps) 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 Nile (PostgreSQL for Multi-Tenant Apps) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Nile Data via Vercel AI SDK

Connect your React frontend directly to your database management layer to provision tenants. When a user requests a new B2B environment, your agent calls `create_tenant` and pipes the provisioning status straight to the browser. No loading spinners. The client watches the virtual boundary form in real time. You can immediately follow up with `list_tenants` to render the updated dashboard without writing custom polling hooks.

Expose Live Database Metrics

Expose live database strain metrics directly to your users. Stop building custom dashboards just to show operational health. Give your AI client the `get_metrics` tool and let it stream performance numbers straight into your Next.js application. Users ask about system health, and the agent pulls exact numbers on the fly. It checks `get_database` for current state details and formats the output into your UI components instantly. This MCP server handles the raw data fetching behind the scenes.

Manage Cross-Tenant Access

Manage global user access across isolated B2B slices. Managing who sees what across different environments gets complicated fast. The MCP integration gives your application direct access to `list_users` so your agent can verify global identities on demand. It pairs perfectly with `list_databases` to map out root connectivity endpoints. You build the interface, and the language model evaluates the permissions.

Setup guide

Set up Nile (PostgreSQL for Multi-Tenant Apps) 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 Nile (PostgreSQL for Multi-Tenant Apps) 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 Nile (PostgreSQL for Multi-Tenant Apps) 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 Nile. 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 Nile (PostgreSQL for Multi-Tenant Apps) 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 Nile (PostgreSQL for Multi-Tenant Apps) MCP in Vercel AI SDK

Install `@ai-sdk/mcp`. Use `createMCPClient` with your endpoint URL, then pass `mcpClient.tools()` into `generateText` or `streamText`. Always call `mcpClient.close()` when the session ends.

Yes. The SDK streams the tool execution results directly to the client. When your agent calls `get_metrics`, the raw performance numbers appear in your UI immediately.

The HTTP transport layer works natively on the edge. You can deploy your Next.js API routes globally and still execute database provisioning commands without cold start penalties.

The MCP client supports an `authProvider` configuration. You pass your OAuth tokens or API keys there, and the connection handles the zero-trust handshake automatically.

The agent reads tenant IDs, database performance numbers, and global user lists. It does not read the actual rows inside your customer tables. The MCP protocol keeps the virtual boundary strictly isolated from the control plane.

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