How to Use the Netdata MCP in Vercel AI SDK

Q: How do I stream active Netdata alarms into my UI using Vercel AI SDK?

You call mcpClient.tools() to register the Netdata tools and pass them to streamText. When the user asks for system health, the agent invokes getalarms and streams the JSON response directly into your React hooks.

Q: Can the Vercel AI SDK handle high-frequency polling with Netdata?

Yes, but you should avoid spamming the API. Use getchartdata selectively within your edge routes to prevent hitting Netdata Cloud rate limits while streaming data to the client.

Feed live Netdata server metrics and active alerts straight into your React components 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 Netdata MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Telemetry Dashboards with Vercel AI SDK

The `get_chart_data` tool pulls raw metric points straight from your nodes, allowing your AI client to render performance graphs on the fly. Instead of making users wait for a slow API poll, the Vercel AI SDK streams these metric values directly into your UI components as they arrive. You don't have to write tedious charting boilerplate anymore. Your agent uses `list_charts` to find the exact CPU or memory metrics it needs, fetches the data, and renders the visual state instantly.

Instant Alarm Auditing in Edge Functions

Running your monitoring tools at the edge keeps latency low. This Netdata MCP Server lets your agent call `get_alarms` inside Vercel Edge Functions, checking every active alert across your infrastructure in milliseconds. When an incident occurs, your application doesn't need to load a heavy dashboard. The agent grabs the status of your nodes using `get_agent_info` and formats the critical alert details for immediate display in your user interface.

Multi-Space Infrastructure Mapping

Navigating complex setups gets messy when you have dozens of environments. By exposing `list_spaces` and `list_rooms` to your agent through this MCP Server, you let the AI map out your entire Netdata Cloud organization dynamically. Once the topology is mapped, the agent uses `list_room_nodes` to pinpoint exactly which machines are throwing errors. The user gets a clear, live-updated tree of their infrastructure without clicking through endless nested menus.

Setup guide

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

You call `mcpClient.tools()` to register the Netdata tools and pass them to `streamText`. When the user asks for system health, the agent invokes `get_alarms` and streams the JSON response directly into your React hooks.

Yes, but you should avoid spamming the API. Use `get_chart_data` selectively within your edge routes to prevent hitting Netdata Cloud rate limits while streaming data to the client.

Vinkius manages the connection, meaning you only need a single endpoint token. You pass this token when setting up `createMCPClient` in your Next.js API route, and it handles the underlying Netdata Cloud authentication.

No. The agent understands the schema returned by this MCP Server tool natively, so it can filter charts and match them to your frontend UI components without manual parsing.

This integration only touches read-only metric metadata, node names, and active alarm states. No raw application data or personal information ever leaves your system, and Vinkius runs the server in an isolated, zero-trust sandbox.

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