How to Use the Ninox MCP in Vercel AI SDK

Q: How does listrecords inside Vercel AI SDK edge functions query Ninox?

The listrecords tool operates with minimal latency inside Vercel AI SDK edge environments. Because the MCP server runs in an isolated sandbox, Ninox database queries execute without cold-start delays.

Q: What happens if a Ninox write operation fails during a Vercel AI SDK stream?

If updaterecord fails in Ninox, the server returns a structured error payload to the Vercel AI SDK. Your Vercel AI SDK application catches this error mid-stream, allowing the UI to roll back the optimistic state update immediately.

Stream Ninox database records directly into your React or Next.js frontend in real-time with 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 Ninox MCP to Vercel AI SDK

Create your Vinkius account to connect Ninox 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 Ninox with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Schema Mapping for Next.js UI

`get_database_schema` inspects the structure of your Ninox tables and feeds it to your Vercel AI SDK application instantly. Your Vercel AI SDK application reads this Ninox schema to construct dynamic forms on your frontend without manual coding.

Streaming Record Updates with the MCP Server

`update_record` modifies specific fields in your Ninox tables and streams the progress directly to your Vercel AI SDK user interface. Instead of waiting for a full page reload, the Vercel AI SDK updates the specific Ninox component as the operation completes.

Direct Script Execution for Complex Queries

`execute_ninox_script` runs calculations directly on the Ninox engine and returns the raw output to your Vercel AI SDK streaming response. Your Vercel AI SDK agent uses this MCP tool to process complex relational Ninox queries that are too heavy for client-side JavaScript.

Setup guide

Set up Ninox 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 Ninox 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 Ninox 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 Ninox. 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 Ninox 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 Ninox MCP in Vercel AI SDK

You pass your Ninox API key as an environment variable when initializing the Vercel AI SDK. The Vercel AI SDK establishes a secure connection via the MCP client, handling all Ninox token handshakes in the background.

Yes, the Vercel AI SDK handles streaming tokens while the MCP server executes `create_records` in your Ninox workspace. Your agent receives progress updates and pushes them to your React frontend in real-time.

The `list_records` tool operates with minimal latency inside Vercel AI SDK edge environments. Because the MCP server runs in an isolated sandbox, Ninox database queries execute without cold-start delays.

If `update_record` fails in Ninox, the server returns a structured error payload to the Vercel AI SDK. Your Vercel AI SDK application catches this error mid-stream, allowing the UI to roll back the optimistic state update immediately.

Your relational Ninox database tables and schema details remain strictly within the Ninox secure cloud. The MCP server acts as an ephemeral proxy, transmitting raw Ninox record payloads directly to your Vercel AI SDK hosting platform without storing any persistent data.

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