Can my agent query specific Datadog metrics using DDQL?

Yes. Use the 'query_metrics' tool. Provide your DDQL query string and the target time range. The agent will fetch the numeric timeseries data directly from Datadog's telemetry datastores.

How do I search for a specific error message across my application logs?

Use the 'search_logs' tool. Provide a query matching your error string and an ISO time boundary. The agent will retrieve the structural extraction of logs matching those parameters to help you identify failures.

Can I see which monitors are currently in an alert state?

Absolutely. The 'list_monitors' tool allows you to filter by group state (e.g., 'alert,warn'). The agent pulls the explicitly configured system triggers to show you which services are currently unhealthy.

Datadog MCP Server for Mastra AI 11 tools — connect in under 2 minutes

Name: Datadog
Availability: InStock
Author: Vinkius

docs.mastra.ai/docs/agents/mcp-tools

Built by Vinkius GDPR 11 Tools SDK

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Datadog through the Vinkius and Mastra agents discover all tools automatically — type-safe, streaming-ready, and deployable anywhere Node.js runs.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

typescript

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

async function main() {
  // Your Vinkius token — get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "datadog": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Datadog Agent",
    instructions:
      "You help users interact with Datadog " +
      "using 11 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with Datadog?"
  );
  console.log(result.text);
}

main();

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Datadog MCP Server

Connect your Datadog account to any AI agent and take full control of your infrastructure monitoring and log management through natural conversation.

Mastra's agent abstraction provides a clean separation between LLM logic and Datadog tool infrastructure. Connect 11 tools through the Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution — deployable to any Node.js host in one command.

What you can do

Metric Auditing — Execute static queries targeting numeric telemetry datastores to resolve specific DDQL metrics objects generated dynamically
Log Investigation — Perform structural extraction matching target string traces inside Datadog logs to evaluate status boundaries across your apps
Monitor Management — Discover explicit system rule endpoints bounding configured triggers against alert metrics to verify health states
Telemetry Extraction — Fetch timestamp arrays natively from numeric logged endpoints to analyze performance trends over specific time intervals
Log Filtering — Apply ISO boundary mappings to compare logging payloads and identify exactly when errors or bottlenecks occurred

The Datadog MCP Server exposes 11 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Datadog to Mastra AI via MCP

Follow these steps to integrate the Datadog MCP Server with Mastra AI.

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.ts and run with npx tsx agent.ts

Explore tools

Mastra discovers 11 tools from Datadog via MCP

Why Use Mastra AI with the Datadog MCP Server

Mastra AI provides unique advantages when paired with Datadog through the Model Context Protocol.

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure — add Datadog without touching business code

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

TypeScript-native: full type inference for every Datadog tool response with IDE autocomplete and compile-time checks

One-command deployment to any Node.js host — Vercel, Railway, Fly.io, or your own infrastructure

Datadog + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the Datadog MCP Server delivers measurable value.

Automated workflows: build multi-step agents that query Datadog, process results, and trigger downstream actions in a typed pipeline

SaaS integrations: embed Datadog as a first-class tool in your product's AI features with Mastra's clean agent API

Background jobs: schedule Mastra agents to query Datadog on a cron and store results in your database automatically

Multi-agent systems: create specialist agents that collaborate using Datadog tools alongside other MCP servers

Datadog MCP Tools for Mastra AI (11)

These 11 tools become available when you connect Datadog to Mastra AI via MCP:

get_dashboard

Resolves all widget configurations, template variables, and layout structures for visualization rendering. Get dashboard details

get_monitor

Resolves notification settings, threshold values, and historical status changes for the given monitor ID. Get monitor details

list_dashboards

Returns a list of dashboard identifiers, titles, layout types (timeboard/screenboard), and direct access URLs. List all dashboards

list_downtimes

Returns scope tags, recurring schedules, and current status to identify planned maintenance periods. List scheduled downtimes

list_events

Returns a collection of events including titles, priority levels, and source identifiers (e.g., monitor alerts, deployment events). List events

list_hosts

Returns host metadata including agent version, active tags, and associated cloud provider attributes. List infrastructure hosts

list_monitors

Filters results by operational state (alert, warn, no data, ok) and returns monitor metadata including type, query, and current status. List monitors by state

list_slos

Returns SLO definitions including target percentages, time windows, and current compliance status for monitor-based or metric-based objectives. List Service Level Objectives

mute_monitor

Interacts with the alerting boundary to set temporary silence periods, optionally with an automatic expiration timestamp. Mute a monitor

query_metrics

Resolves time-series data within the specified UNIX timestamp range. Returns metric points, scope tags, and unit metadata for infrastructure and application monitoring. Query time-series metrics

search_logs

Interacts with the log storage boundary to retrieve entries matching the query syntax, including timestamps, status levels, and structured attributes. Search application logs