How to Use the Datadog AI (LLM Observability) MCP in Vercel AI SDK

Q: How can I show live Datadog AI (LLM Observability) metrics in my app using the Vercel AI SDK?

Just call the querymetrics tool. The Vercel AI SDK is built for streaming, so you can pipe the metric data directly into your React or Svelte components. Your users will see the numbers change in real-time.

Q: Can my frontend app create alerts in Datadog AI (LLM Observability) with the Vercel AI SDK?

Yes, that's what the createmonitor tool is for. You can build a form in your UI that lets an admin set up a new monitor. The MCP Server handles the connection to Datadog.

Q: What's the best way to list incidents from Datadog AI (LLM Observability) in a Vercel AI SDK project?

Use the listincidents tool. It's designed to fetch active incidents. Since you're using the AI SDK, you can stream these into a list that updates automatically as new incidents are created or resolved.

Q: Can I search through specific LLM interactions?

Absolutely. The searchllmspans tool is what you need. It lets you find and display detailed traces of your AI's operations, which is great for debugging or audit trails.

Stream Datadog AI metrics and events directly into your Next.js app with the Vercel AI SDK. No loading spinners, just live data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datadog AI (LLM Observability) MCP to Vercel AI SDK

Create your Vinkius account to connect Datadog AI (LLM Observability) 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 AI (LLM Observability) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live LLM Token Usage in Your UI

The `query_metrics` tool lets you pull `datadog.llm_observability.tokens` in real time. Instead of waiting for a report, your user can watch their token count update live in the dashboard you build. It's perfect for building transparent, pay-as-you-go AI features. You can also use `submit_series` to push custom data points from your app back to Datadog. This means your frontend can report on user interactions or client-side performance, then you can correlate it with your LLM's behavior.

Display Incidents and Events Instantly

Use the `list_incidents` and `list_events` tools to build a live status page or an admin dashboard. When your AI client triggers a new incident in Datadog, the Vercel AI SDK streams that data directly to your UI, so your support team sees it immediately. This MCP Server also lets you dig deeper. With `search_llm_spans`, you can find specific AI interactions and display the full trace, giving your users or admins a complete picture of what happened.

Manage Monitors with the Vercel AI SDK

Let your users configure their own alerting from your app's settings page. The `create_monitor` tool sends a request to Datadog to set up a new AI monitor based on user input. You can then confirm the monitor was created or list existing ones with `list_ai_monitors`. Because the AI SDK streams results, the UI can update from "creating..." to "active" without a page refresh, which feels a lot smoother.

Setup guide

Set up Datadog AI (LLM Observability) 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 AI (LLM Observability) 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 AI (LLM Observability) 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 AI (LLM Observability) 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 AI (LLM Observability) MCP in Vercel AI SDK

Just call the `query_metrics` tool. The Vercel AI SDK is built for streaming, so you can pipe the metric data directly into your React or Svelte components. Your users will see the numbers change in real-time.

Yes, that's what the `create_monitor` tool is for. You can build a form in your UI that lets an admin set up a new monitor. The MCP Server handles the connection to Datadog.

Use the `list_incidents` tool. It's designed to fetch active incidents. Since you're using the AI SDK, you can stream these into a list that updates automatically as new incidents are created or resolved.

Absolutely. The `search_llm_spans` tool is what you need. It lets you find and display detailed traces of your AI's operations, which is great for debugging or audit trails.

No, your credentials stay on the server. The Vinkius MCP Server manages the Datadog connection securely. Your client only needs a single Vinkius endpoint token to access tools that query LLM spans and metrics.

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