Datadog
The MCP server provides an interface to the Datadog API, enabling seamless management of incidents, monitoring, logs, dashboards, metrics, traces, and hosts. Its extensible design allows easy integration of additional Datadog APIs for future expansio
What is Datadog?
Datadog is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server provides an interface to the datadog api, enabling seamless management of incidents, monitoring, logs, dashboards, metrics, traces, and hosts. its extensible design allows easy integration ...
The MCP server provides an interface to the Datadog API, enabling seamless management of incidents, monitoring, logs, dashboards, metrics, traces, and hosts. Its extensible design allows easy integration of additional Datadog APIs for future expansio
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The MCP server provides an interface to the Datadog API, ena
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @winor30/mcp-server-datadogManual Installation
npx -y @winor30/mcp-server-datadogConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Datadog
The Datadog MCP Server is a community-maintained TypeScript server that exposes the Datadog API as MCP tools, enabling AI assistants to manage and query incidents, monitors, logs, dashboards, metrics, APM traces, RUM events, and hosts without leaving the chat interface. It covers the full operational workflow from listing active incidents and checking monitor states to scheduling maintenance downtimes and querying page performance via Real User Monitoring. Engineering teams use it to give on-call engineers and AI coding assistants a conversational interface to their Datadog observability stack.
Prerequisites
- A Datadog account with API access
- A Datadog API key (DD_API_KEY) from your Datadog organization settings
- A Datadog Application key (DD_APP_KEY) from your Datadog organization settings
- Node.js 18 or higher and npx available
- An MCP-compatible client such as Claude Desktop
Obtain your Datadog API and Application keys
In the Datadog web UI, navigate to Organization Settings > API Keys to create or copy your API key, and Organization Settings > Application Keys to create an application key with the required permissions.
Test the server with npx
Run the server directly using npx to verify it starts correctly before configuring your MCP client.
DD_API_KEY=your_api_key DD_APP_KEY=your_app_key npx -y @winor30/mcp-server-datadogConfigure your MCP client
Add the Datadog MCP server to your client's configuration file, passing the API credentials as environment variables. The server communicates via stdio.
Verify tool availability
Once connected, ask your AI client to list available tools or run a simple query such as listing active Datadog monitors to confirm the connection is working.
Datadog Examples
Client configuration
Claude Desktop configuration using npx to run the Datadog MCP server with API credentials provided as environment variables.
{
"mcpServers": {
"datadog": {
"command": "npx",
"args": ["-y", "@winor30/mcp-server-datadog"],
"env": {
"DD_API_KEY": "your_datadog_api_key",
"DD_APP_KEY": "your_datadog_application_key",
"DD_SITE": "datadoghq.com"
}
}
}
}Prompts to try
Example prompts using the 20+ tools exposed by the Datadog MCP server.
- "List all active Datadog incidents and summarize their current status"
- "Query the logs for errors in the api-gateway service in the last 2 hours"
- "Show me the CPU usage metric for host web-01 over the last 30 minutes"
- "Schedule a downtime for host:db-replica from now until midnight for planned maintenance"
- "Get the RUM page performance metrics for our checkout view from the last 24 hours"Troubleshooting Datadog
API returns 403 Forbidden for incident or monitor operations
Application keys in Datadog have scoped permissions. Ensure the application key was created by a user with the required role (e.g., Datadog Admin) and that the key has not been revoked. Create a new application key with appropriate permissions if needed.
Server starts but returns empty results for logs or traces
The 'from' and 'to' parameters for log and trace queries are epoch timestamps in seconds. Verify the time range is correct and that logs exist in Datadog for that period. Use 'Math.floor(Date.now()/1000) - 3600' for the past hour.
DD_SITE environment variable not set causes connection to wrong region
If your Datadog account is on a non-US region (e.g., EU), set DD_SITE to the appropriate value such as 'datadoghq.eu' or 'us3.datadoghq.com'. The default is 'datadoghq.com' which only works for US1 accounts.
Frequently Asked Questions about Datadog
What is Datadog?
Datadog is a Model Context Protocol (MCP) server that mcp server provides an interface to the datadog api, enabling seamless management of incidents, monitoring, logs, dashboards, metrics, traces, and hosts. its extensible design allows easy integration of additional datadog apis for future expansio 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 @winor30/mcp-server-datadog. 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 Apache 2.0 license. You can use it freely in both personal and commercial projects.
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
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-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
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis 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
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry 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.
Set Up Datadog in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.