Language:JapaneseEnglish

datadog Claude Code Plugin

Author
Datadog
Category
Monitoring
Topics
Monitoring & Observability · AI Agents & AI App Development
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-07-12 (UTC)
Source (GitHub) last updated
2026-08-19 (UTC) (8 days ago)

The explanation below is AI-generated. Please verify it against the sources.

This is a Claude Code plugin (currently in Preview) that connects Claude Code to a preconfigured Datadog MCP server, letting you query Datadog logs, metrics, traces, dashboards, and monitors using natural language. It requires a Datadog account and Claude Code v2.1.30+, and is installed via /plugin install datadog@claude-plugins-official. Setup connects the plugin to your Datadog account and selects the correct Datadog MCP domain, either through OAuth in the browser or via API key/application key environment variables. According to the README, no Datadog credentials are sent to the AI model provider.

About the service

Datadog, per its homepage, is described as 'Cloud Monitoring as a Service' — an integrated observability and security platform covering infrastructure, applications, logs, security, digital experience, software delivery, and service management.

What you can do with datadog

  • Ask natural-language questions about Datadog logs, metrics, traces, dashboards, and monitors (e.g., "Show me error logs from the last hour")
  • Check which monitors are currently alerting
  • Find traces for a specific service filtered by conditions such as latency
  • List your dashboards
  • Run /ddsetup to connect the plugin to your Datadog account and select the MCP domain
  • Run /ddconfig to change your Datadog site, switch organizations, or diagnose connection issues
  • Run /ddtoolsets to enable or disable groups of tools
  • Authenticate via OAuth (default) or via Datadog API key and application key environment variables (DD_MCP_DOMAIN, DD_API_KEY, DD_APPLICATION_KEY)

Sources

Back to list