Datadog MCP Server

🚀 Datadog MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to directly search and analyze Datadog logs. This integration allows AI assistants to query your Datadog logs using natural language, enhancing the efficiency of troubleshooting and log analysis.

✨ Features

• Log Search: Search for logs in Datadog using flexible query parameters.
• Time-based Filtering: Filter logs based on a specific time range.
• Pagination Support: Navigate large log sets through cursor pagination.
• Coming Soon: Metrics retrieval functionality.

📦 Installation

Prerequisites

• A Datadog account with API access.
• Datadog API and application keys (see documentation for details).

Setup

Add the MCP server configuration to your AI assistant's MCP settings file:

⚠️ Important Note

This MCP server only supports stdio transport. SSE transport is not available.

"datadog-mcp-server": {
  "command": "npx",
  "args": ["-y", "@i524/datadog-mcp-server"],
  "env": {
    "DD_API_KEY": "<your-datadog-api-key>",
    "DD_APP_KEY": "<your-datadog-app-key>"
  }
}

💻 Usage Examples

Available Tools

search-logs

Search for logs from Datadog using flexible filtering options.

Parameters:

• filterQuery (Required): A query string for filtering logs. Refer to Datadog Log Search Syntax for details.
• filterFrom (Optional): The minimum timestamp (ISO 8601 format) for requesting logs.
• filterTo (Optional): The maximum timestamp (ISO 8601 format) for requesting logs.
• cursor (Optional): A cursor for pagination.

Example Usage:

// Search for error logs of a specific service in the production environment
{
  "filterQuery": "service:awesome-service status:error",
  "filterFrom": "2025-01-01T00:00:00Z",
  "filterTo": "2025-01-02T00:00:00Z"
}

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.