▌BestMCPTools.org
Datadog MCP logo

Datadog MCP

Query Datadog logs, metrics, traces and incidents from your AI tools

Developer ToolsFreemiumAll ModelsModerate
Visit Tool45 stars

Last verified: August 17, 2026

Own Datadog MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 25, 2026License: MITChecked September 28, 2026

How to Install Datadog MCP

$npx -y @datadog/mcp-server

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "datadog-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@datadog/mcp-server"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "datadog-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@datadog/mcp-server"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "datadog-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@datadog/mcp-server"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add datadog-mcp -- npx -y @datadog/mcp-server

Add any API keys or environment variables the server's README lists.

About Datadog MCP

Datadog's official MCP server connects AI agents to the observability platform, querying logs, metrics, APM traces, monitors and incidents directly from Claude, Cursor or VS Code. The practical win is incident triage: an agent can pull the error rate, correlate it against a recent deploy and surface the offending trace without anyone opening a dashboard. Access is scoped by Datadog API and app keys. Teams on open-source dashboards can use the Grafana MCP setup, and for application errors the Sentry MCP setup adds stack traces to the same investigation.

Key Features

  • observability
  • monitoring
  • logs
  • apm
  • incidents

Pricing

Freemium: from Free with Datadog plan

Pros & Cons

Pros

  • Acts more like a pair programmer with real tools
  • Tight scoping (one repo, dry-run) limits blast radius
  • Keeps flow inside the editor

Cons

  • Write operations require explicit guardrails
  • Quality of output depends on repo hygiene
  • Larger monorepos may need extra filtering

Best For

  • Reviewing diffs and opening PRs from chat
  • Triaging CI failures
  • Scaffolding new packages or modules
  • Repo-wide refactors with verification

Our Take on Datadog MCP

Turns incident triage into a conversation. Worth wiring up if Datadog is already your source of truth for production.

Frequently Asked Questions

Tags

#Developer Tools#observability#monitoring#logs#apm#incidents