How to Use the ncScale MCP in Vercel AI SDK

Q: How do I stream active ncScale alerts to a Next.js frontend using the Vercel AI SDK?

You install the @ai-sdk/mcp package and pass the server's HTTP endpoint to createMCPClient. From there, call the listalerts tool inside streamText to let your UI render incoming system issues in real-time.

Q: How does the Vercel AI SDK handle tool calling with ncScale?

The SDK automatically executes tools like listtickets or listdashboards when the agent needs context. This MCP integration feeds tool outputs back into the LLM context, which then streams the final diagnostic response to your user interface.

Q: How do I handle authentication for this server in my app?

You pass your credentials through the authProvider when initializing the client. This keeps your API keys secure while letting the agent query listusers or workspace details on behalf of your logged-in team members.

Q: What happens to my no-code logs and alerts when using this server?

Your monitoring data, including payloads from listlogs and getalert, passes directly through an ephemeral, zero-trust sandbox. The system never stores your API keys or logs on disk, ensuring your operational metadata stays private.

Stream live no-code health metrics directly into your Next.js frontend using the Vercel AI SDK and ncScale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live incident feeds in your Vercel AI SDK app

Your users don't want to reload a page to see if their Bubble app is breaking. When you pair this MCP Server with the Vercel AI SDK, your AI client pulls live incidents via `list_alerts` and streams them straight to your React components. The data renders on the screen block-by-block while the request is still finishing. You can build a custom system dashboard that renders node failures instantly. Your application calls `get_node` inside an Edge Function, letting the end user inspect specific failing elements in their Airtable or Bubble integrations without staring at a blank loading spinner.

On-the-fly log inspection at the edge

Running your AI clients on Edge Functions means you need light, fast connections. This integration lets you stream active system logs via `list_logs` directly into a terminal-like interface on your frontend. The Vercel AI SDK handles the data stream without cold starts, letting developers check live no-code execution steps instantly. If an error pops up, the user can ask the agent to explain it. The agent calls `get_alert` to fetch the error payload and streams the explanation line-by-line, making debugging feel instant.

Interactive workspace diagnostics

Give your team a chat interface that can actually inspect your no-code stack. By exposing `list_integrations` and `get_workspace_info` to the Vercel AI SDK via this MCP Server, your support team can query which external tools are active and see the results load dynamically in their chat bubble. Instead of jumping between tabs, they type a question and watch the agent pull workspace metadata. The agent formats the active connections into clean UI cards as the JSON payload streams in from the server.

Setup guide

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

You install the `@ai-sdk/mcp` package and pass the server's HTTP endpoint to `createMCPClient`. From there, call the `list_alerts` tool inside `streamText` to let your UI render incoming system issues in real-time.

Yes, the server is compatible with Edge runtimes because it relies on lightweight HTTP transport. Your Vercel AI SDK agent can call `list_logs` and `get_node` without hitting node-specific runtime limits or causing cold starts.

The SDK automatically executes tools like `list_tickets` or `list_dashboards` when the agent needs context. This MCP integration feeds tool outputs back into the LLM context, which then streams the final diagnostic response to your user interface.

You pass your credentials through the `authProvider` when initializing the client. This keeps your API keys secure while letting the agent query `list_users` or workspace details on behalf of your logged-in team members.

Your monitoring data, including payloads from `list_logs` and `get_alert`, passes directly through an ephemeral, zero-trust sandbox. The system never stores your API keys or logs on disk, ensuring your operational metadata stays private.

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