How to Use the Datadog MCP in Vercel AI SDK

Q: How do I stream Datadog metrics live using the Vercel AI SDK?

You pass the querymetrics tool from this MCP Server directly into streamText. The SDK handles the raw telemetry data stream, letting your React components render the metrics charts in real-time.

Stream real-time Datadog metrics and active incidents directly into your Next.js frontend 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 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

Build live Datadog dashboard views in Vercel AI SDK

When your Datadog alerts trigger, your Vercel AI SDK frontend shouldn't make users wait for a loading spinner. This MCP Server lets your application stream raw infrastructure status directly into React components by calling `get_dashboard` and `list_hosts` on the fly. Your Next.js edge route handles the streaming text, rendering live host lists and active metrics as they arrive. Users see exactly which servers are spiking without refreshing a single page.

Query Datadog logs straight to your frontend

Stop writing custom API endpoints for every single monitoring query when this MCP Server lets your AI client invoke `search_logs` and `query_metrics` to pull telemetry data directly into the Vercel AI SDK stream. The frontend displays raw log lines and metrics charts instantly. You get clean JSON back from the server, letting your UI format the Datadog logs while the LLM explains the error.

Mute noisy monitors from your Vercel AI SDK chat

Give your team the power to quiet alerts without opening a dozen tabs by letting your AI client call `mute_monitor` or `list_monitors` over the MCP protocol based on natural language commands. Because the Vercel AI SDK handles tool calls natively on the edge, the mute action registers instantly in your Datadog account, keeping your Slack channel quiet during scheduled maintenance.

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

You pass the `query_metrics` tool from this MCP Server directly into `streamText`. The SDK handles the raw telemetry data stream, letting your React components render the metrics charts in real-time.

Yes, this server is fully compatible with Edge runtimes. Your agent calls `search_logs` to scan your log groups, and the results stream back to your frontend without hitting cold start delays.

Vinkius manages the secure connection to your Datadog API keys. You configure the MCP client once with your Vinkius endpoint token, and the SDK safely routes all monitor and incident requests.

The Vercel AI SDK catches the tool execution error directly in your edge route. Your UI can display a fallback component while the agent suggests trying a different query or checking connectivity with `check_datadog_status` over the MCP connection.

Vinkius runs the server in an ephemeral V8 sandbox, meaning your active incident details and log payloads are never stored on our disks. Only the raw, encrypted transit data passes through your Vercel AI SDK connection to fetch active issues from the MCP Server.

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