Datadog MCP server

Datadog is the essential monitoring and observability platform for cloud-scale applications, providing comprehensive visibility across infrastructure, applications, logs, and user experience. With this MCP server, AI agents can query metrics, search logs, manage monitors, create dashboards, and generate insights through natural language commands.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.

Before you begin

You'll need:

• Access to AI Gateway with permission to create MCP servers.
• API credentials for the application you're connecting (see the Authentication section on this page for what to collect).

Create an MCP server

Find the app in the catalog

1. Sign in to AI Gateway and select App Catalog from the left navigation.
2. Search for the application you want to connect, then select it from the catalog.
3. Select Create MCP Server to start the wizard.

App Configuration

Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.

MCP Server Setup

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose.
2. Enter a Description so your team knows what the server is for.
3. Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
4. Select Next.

Authentication

Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.

Review

Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

---

Connect to an AI client

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

Tips

• You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
• If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.

Authentication

Datadog uses API key and application key authentication. Generate both from your Datadog organization settings under Organization Settings > API Keys and Application Keys.

Value	Setting
API key header	DD-API-KEY: {your-api-key}
Application key header	DD-APPLICATION-KEY: {your-application-key}
Base URL (US1)	https://api.datadoghq.com
Base URL (EU1)	https://api.datadoghq.eu
Base URL (US3)	https://api.us3.datadoghq.com
Base URL (US5)	https://api.us5.datadoghq.com
Base URL (AP1)	https://api.ap1.datadoghq.com

Available tools

The Datadog MCP server exposes metrics, logs, monitors, dashboards, events, APM, and synthetic monitoring APIs.

Tool	Purpose
Metrics Query	Retrieve time series data; aggregate metrics across tags; run calculations and transformations
Logs Search	Search log events; aggregate log data; access log archives; configure pipelines
Monitors	Create and manage monitors; configure alert conditions; set notification rules
Dashboards	Create custom dashboards; add widgets (time series, query values, heatmaps); share dashboards
Events	Submit custom events; query event stream; correlate with metrics; tag and filter events
APM Services	View service dependencies; track performance metrics; analyze error rates; manage SLOs
Synthetic Tests	Create API tests; run multi-step browser tests; schedule from global locations

Tips

Use consistent tagging conventions across your infrastructure.

Tag by environment and application and leverage tag-based filtering for faster queries.

Set thresholds that reduce alert fatigue.

Use appropriate alert evaluation windows and configure escalation policies for critical services.

Use composite alerts for multi-condition scenarios.

Create focused dashboards for specific use cases rather than overly broad dashboards.

Use template variables for dynamic filtering and organize dashboards by team or service.

Use log pipelines to extract and parse important fields.

Configure log indexes to balance retention and cost.

Create saved views for common search patterns.

Set up synthetic tests from multiple geographic locations.

Track key user journeys through your application.

Use error tracking to understand failure patterns.

Configure SLO alerts for critical services.

---