Datadog MCP Server Integration

What does “Datadog” MCP Server do?

The Datadog MCP Server is a Model Context Protocol (MCP) server designed to bridge AI assistants and the official Datadog API. By acting as an intermediary, it enables AI-based tools and agents to access, query, and manage monitoring data, dashboards, metrics, events, logs, and incidents from Datadog accounts. This integration empowers developers and operators to automate monitoring tasks, perform advanced queries, and interact with Datadog resources directly from their AI workflows or assistants. The server supports both Datadog v1 and v2 APIs, providing comprehensive access to service endpoints, enhanced error handling, and the ability to specify regional or service-specific endpoints for logs and metrics. Ultimately, it streamlines workflows related to observability and incident management by making Datadog’s capabilities accessible within broader AI-driven automation and development environments.

List of Prompts

No explicit prompt templates are mentioned in the available documentation or code.

List of Resources

• Monitoring data — Access monitor data and configurations from Datadog.
• Dashboards — Retrieve and view dashboard definitions stored in Datadog.
• Metrics — Query available metrics and their metadata from Datadog’s API.
• Events — Search and retrieve Datadog events within defined timeframes.
• Logs — Search logs with advanced filtering and sorting options from Datadog.

List of Tools

No explicit list of tools (as MCP tools) is available in the documentation or server source tree as presented. The functionalities (monitoring, dashboards, etc.) are likely implemented as tools, but are not enumerated as discrete MCP tools in the documentation.

Use Cases of this MCP Server

• Monitoring Automation: Automate the retrieval and management of monitor configurations, enabling instant insights and rapid responses to changes in system health.
• Dashboard Exploration: Seamlessly fetch and review dashboard definitions, making it easier for AI agents or users to analyze, share, and update monitoring dashboards.
• Metric Analysis: Query and analyze a wide range of metrics and metadata, supporting detailed performance investigations, anomaly detection, or custom visualization generation.
• Incident & Event Management: Search and retrieve events or incident data, allowing AI workflows to automate incident review, escalate issues, or summarize postmortems.
• Log Search and Filtering: Execute advanced log queries with filtering and sorting, facilitating real-time troubleshooting and root cause analysis via AI-driven tools.

How to set it up

Windsurf

No explicit Windsurf setup instructions are given in the documentation.

Claude

1. Ensure you have Node.js (v16+) and a Datadog account with API and Application keys.
2. Install the package globally or use npx.
3. Locate your claude_desktop_config.json configuration file.
4. Add the Datadog MCP server configuration under the mcpServers object:

   {
     "mcpServers": {
       "datadog": {
         "command": "npx",
         "args": [
           "datadog-mcp-server",
           "--apiKey",
           "<YOUR_API_KEY>",
           "--appKey",
           "<YOUR_APP_KEY>",
           "--site",
           "<YOUR_DD_SITE>(e.g us5.datadoghq.com)"
         ]
       }
     }
   }
   

5. Save the file and restart Claude Desktop to apply the changes.

Advanced configuration with service-specific endpoints:

{
  "mcpServers": {
    "datadog": {
      "command": "npx",
      "args": [
        "datadog-mcp-server",
        "--apiKey", "<YOUR_API_KEY>",
        "--appKey", "<YOUR_APP_KEY>",
        "--site", "<YOUR_DD_SITE>",
        "--logsSite", "<YOUR_LOGS_SITE>",
        "--metricsSite", "<YOUR_METRICS_SITE>"
      ]
    }
  }
}

Securing API Keys using environment variables:

{
  "mcpServers": {
    "datadog": {
      "command": "npx",
      "args": [
        "datadog-mcp-server"
      ],
      "env": {
        "DD_API_KEY": "<YOUR_API_KEY>",
        "DD_APP_KEY": "<YOUR_APP_KEY>"
      }
    }
  }
}

Cursor

No explicit Cursor setup instructions are given in the documentation.

Cline

No explicit Cline setup instructions are given in the documentation.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "datadog": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent can use this MCP as a tool with access to all its functions and capabilities. Remember to change “datadog” to the actual name of your MCP server and replace the URL with your own MCP server URL.

Overview

Roots support: ⛔ (Not mentioned)

Based on the completeness of the documentation, presence of setup instructions for Claude, and resource listing, but lack of prompt templates, MCP-tool enumeration, and Roots/Sampling support, we would rate this MCP server as moderately mature and ready for practical integration in AI workflows.

MCP Score