MCPgee
MCPgee
MCPgeeMCPgee

Datadog

v1.0.9•Monitoring & Observability•stable

MCP server interacts with the official Datadog API

datadogmcpmodel-context-protocolobservabilityapi
Share:
67
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Datadog?

Datadog is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server interacts with the official datadog api

MCP server interacts with the official Datadog API

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server interacts with the official Datadog API

Use Cases

Monitor application observability with Datadog.
Query metrics and logs through AI.
Manage alerts and dashboard data naturally.
GeLi2001

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.9
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y datadog-mcp-server

Manual Installation

npx -y datadog-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Datadog

The Datadog MCP server connects Claude and other AI assistants to the official Datadog API, exposing tools for querying monitors, dashboards, metrics, events, logs, and incidents in natural language. Rather than switching between the Datadog web UI and your terminal, engineers can ask Claude to investigate alerts, search error logs, or pull metric metadata directly in the conversation. It supports all Datadog site regions and requires a standard Datadog API key plus an Application key.

Prerequisites

  • Node.js 16 or higher
  • A Datadog account with at least one active organization
  • A Datadog API key and an Application key (found under Organization Settings → API Keys and App Keys)
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Install the package

Install the Datadog MCP server globally via npm so it is available as a command on your PATH.

npm install -g datadog-mcp-server
2

Locate your Datadog credentials

In the Datadog web app go to Organization Settings → API Keys to find or create your DD_API_KEY, and to App Keys for your DD_APP_KEY. Note your site (e.g. datadoghq.com or datadoghq.eu).

3

Test the server from the command line

Run the server directly to confirm credentials are accepted before wiring it into your MCP client.

datadog-mcp-server --apiKey=YOUR_API_KEY --appKey=YOUR_APP_KEY --site=datadoghq.com
4

Add to your MCP client configuration

Edit claude_desktop_config.json to register the Datadog MCP server. Pass your credentials as command-line arguments so they are available at startup.

5

Restart your MCP client and verify

Restart Claude Desktop or run claude mcp list to confirm the server appears. Ask Claude to list your Datadog monitors to verify connectivity.

Datadog Examples

Client configuration

Add this block to claude_desktop_config.json, replacing the placeholder values with your real Datadog API key, application key, and site.

{
  "mcpServers": {
    "datadog": {
      "command": "npx",
      "args": [
        "-y",
        "datadog-mcp-server",
        "--apiKey", "YOUR_DD_API_KEY",
        "--appKey", "YOUR_DD_APP_KEY",
        "--site", "datadoghq.com"
      ]
    }
  }
}

Prompts to try

Once connected, use these prompts to interact with Datadog through Claude.

- "Show me all currently triggered Datadog monitors."
- "Search logs for service:web-app status:error in the last 15 minutes."
- "List all dashboards and give me a summary of what each one tracks."
- "Get the metadata for the aws.ec2.cpuutilization metric."
- "Show me all active incidents and their current severity levels."

Troubleshooting Datadog

Authentication error: 'Invalid API key'

Double-check that both DD_API_KEY and DD_APP_KEY are correct and belong to the same Datadog organization. Application keys are user-scoped — ensure the key has the necessary permissions (Monitors Read, Logs Read, etc.).

Tools return empty results even though data exists in Datadog

Verify the --site parameter matches your Datadog region. EU customers should use datadoghq.eu and US1-FED customers use ddog-gov.com. An incorrect site sends requests to the wrong endpoint.

npx fails to find datadog-mcp-server

Run npm install -g datadog-mcp-server to install globally, then confirm with which datadog-mcp-server. Alternatively use the full npx -y datadog-mcp-server invocation which downloads on demand.

Frequently Asked Questions about Datadog

What is Datadog?

Datadog is a Model Context Protocol (MCP) server that mcp server interacts with the official datadog api It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Datadog?

Install via npm with the command: npx -y datadog-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Datadog?

Datadog works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Datadog free to use?

Yes, Datadog is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Datadog Alternatives — Similar Monitoring & Observability Servers

Looking for alternatives to Datadog? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.

Netdata

★ 78.9k

Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.

Kubeshark

★ 11.9k

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

Mission Control

★ 4.9k

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

Grafana

★ 3.0k

This MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.

Sentrux

★ 2.4k

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

OpenInference

★ 986

OpenTelemetry Instrumentation for AI Observability

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Monitoring & ObservabilityBrowse All Servers

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Datadog?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides