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

Q: Does this MCP Server let me manage Datadog dashboards?

You can list them. The listdashboards tool enumerates your existing dashboards, which is useful for workflows that need to check if a specific reporting dashboard is present before proceeding.

Build resilient Datadog monitoring workflows with Mastra AI. Automate incident response, manage monitors, and handle failures gracefully.

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 Mastra AI

Create your Vinkius account to connect Datadog AI (LLM Observability) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Incident Triage Workflows

The `list_incidents` tool is your starting point for an automated response workflow. When it finds a new incident, Mastra AI's engine can trigger a series of steps: use `search_llm_spans` to get context, then `create_event` to post findings to a timeline. Mastra's strength is conditional logic. If `search_llm_spans` returns a high-priority customer, your workflow can automatically escalate. If the search fails, the built-in retry mechanism will try again before giving up.

Proactive LLM Monitor Management

Use `list_ai_monitors` to periodically check the health of your Datadog monitors themselves. If a monitor is misconfigured, you can build a workflow that uses `create_monitor` to replace it with a corrected version. This is perfect for maintaining observability at scale. You can define your ideal monitoring state in code, and have a Mastra AI agent constantly enforce it, fixing any drift it finds in your Datadog setup. This MCP Server gives you the tools to do it.

Build Complex Reporting with Mastra AI

Chain together multiple tools for deep analysis. A workflow could start by using `list_service_accounts`, loop through each one to `query_metrics` for token usage, and then `submit_series` with aggregated data to create a custom summary metric. You don't have to worry about one of the API calls failing. Mastra AI can be configured to log the error, skip to the next service account, and continue its work. That's how you build reliable, long-running data jobs.

Setup guide

Set up Datadog AI (LLM Observability) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Datadog AI (LLM Observability) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "datadog-ai-llm-observability-mcp-client",
  servers: {
    "datadog-ai-llm-observability-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Datadog AI (LLM Observability) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Datadog AI (LLM Observability) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Datadog AI (LLM Observability) transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI has built-in automatic retries with exponential backoff. If a tool like `list_incidents` fails because of a network blip, the agent will try again. You can define complex failure logic, like trying an alternative tool or notifying an admin.

Yes, that's a classic Mastra AI pattern. Your workflow would call `create_monitor`, then in the next step, call `list_ai_monitors` with a filter to confirm the new monitor exists and is configured correctly.

A solid use case is building an automated cost-auditing agent. The agent can use `query_metrics` to check token usage against a budget, and if it exceeds a threshold, use `create_event` to flag the responsible service account for review.

You can list them. The `list_dashboards` tool enumerates your existing dashboards, which is useful for workflows that need to check if a specific reporting dashboard is present before proceeding.

The connection is handled by the Vinkius platform, which isolates every request. Your agent uses a single access token, and the MCP Server handles the actual Datadog authentication on the backend, so your sensitive credentials for Datadog are never exposed to the agent's environment. The server only processes data like LLM metrics and event details.

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