Dynatrace MCP Server

This project implements a Model Context Protocol (MCP) server that provides an interface to interact with Dynatrace Grail and API endpoints.

Features

• DQL Execution: Execute arbitrary Dynatrace Query Language (DQL) queries.

• Log Retrieval: Fetch and filter application logs.

• Problem Reporting: Get current active problems from Dynatrace.

• Metric Querying: Query metrics using DQL.

Related MCP server: Dynatrace Managed MCP Server

Prerequisites

• Python 3.14+

• A Dynatrace environment with API access tokens.

Setup

1. Environment Variables: Create a .env file in the root directory with the following variables:

   DYNATRACE_URL=<your-dynatrace-url>
   DYNATRACE_API_TOKEN=<your-api-token>
   DYNATRACE_PLATFORM_URL=<your-platform-url>
   DYNATRACE_PLATFORM_TOKEN=<your-platform-token>
   DYNATRACE_LOG_INGEST_TOKEN=<your-log-ingest-token>

2. Dependencies: Install the required dependencies:

   pip install -r requirements.txt

Usage

Start the MCP server:

python server.py

Add this into gemini/settings.json

"mcpServers": {
   "dynatrace": {
   "command": "D:\\Dynatrace_MCP\\venv\\Scripts\\python.exe",
   "args": [
      "D:\\Dynatrace_MCP\\server.py"
   ]
   }
}

After that run gemini CLI