How to Use the Datadog MCP in Vercel AI SDK

Q: How do I stream Datadog metrics to a React component using Vercel AI SDK?

Call querymetrics inside your streamText function. The SDK streams the time-series points directly to your client-side charts.

Q: Can I mute alerts directly from my Next.js chat interface?

Yes, your agent calls mutemonitor with your specified monitor ID and duration. The change reflects instantly in your Datadog dashboard.

Pipe live Datadog metrics and log streams directly into your Next.js UI using the Vercel AI SDK without annoying loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Datadog Metrics Live with Vercel AI SDK

`query_metrics` feeds raw time-series data directly to your streaming Vercel AI SDK UI components. This tool pulls metric points and scope tags over HTTP, bypassing the need for custom backend API endpoints to fetch telemetry. Your users watch performance charts render frame-by-frame as your agent retrieves real-time infrastructure data. No loading spinners or stale page refreshes, just raw Datadog data delivered straight to the Edge.

Interactive Log Exploration in Next.js

`search_logs` targets specific application error logs and brings structured log attributes straight into your interactive chat interface. The client processes these logs on the edge, rendering stack traces and status levels as they stream. Developers trace system failures by telling your agent to pull logs and render them inside custom UI cards. You skip the Datadog console entirely and inspect production errors right inside your application workflow.

Instant Monitor Status Updates via MCP Server

`list_monitors` checks your alerting infrastructure state, letting your agent instantly display active warnings or critical alerts in your app. The MCP Server queries Datadog's API and formats the raw alert payloads for immediate UI rendering. You can also execute `mute_monitor` directly from a chat prompt when an on-call engineer needs to silence a noisy alert. The UI updates instantly to show the new expiration timestamp and active silence status.

Setup guide

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

Call `query_metrics` inside your `streamText` function. The SDK streams the time-series points directly to your client-side charts.

Yes. The server connects via standard HTTP transport, making it lightweight enough to run within Edge execution limits.

The SDK passes MCP tool execution calls directly to the Vinkius managed endpoint. Vinkius handles the underlying connection pooling to prevent API rate exhaustion.

Yes, your agent calls `mute_monitor` with your specified monitor ID and duration. The change reflects instantly in your Datadog dashboard.

The server accesses your raw telemetry, log messages, and monitor states. All API tokens remain isolated inside Vinkius's V8 sandboxed environment and never touch the browser.

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