dt-mcp-server: Skill for Claude Code

Dynatrace Dashboard Skill

Overview

Dynatrace dashboards are JSON documents stored in the Document Store. Each dashboard contains:

• Tiles: Visual components displaying markdown content or data visualizations
• Layouts: Grid-based positioning (20-unit width) defining tile placement
• Variables: Dynamic parameters ($VariableName) for query filtering
• Configuration: Version metadata and dashboard-level settings

When to use this skill:

• Creating new dashboards with skill-based query generation
• Modifying existing dashboards (queries, tiles, layouts)
• Querying dashboard JSON to extract data or analyze structure
• Analyzing dashboard purpose, metrics coverage, and health

Four main workflows:

1. Creating - Build dashboards with skill-based queries
2. Modifying - Update tiles, queries, layouts, variables
3. Querying - Extract data from dashboard JSON
4. Analyzing - Understand structure, purpose, gaps, and health

Dashboard Document Structure

Dashboards in the Dynatrace Document Store include both metadata and content:

{
  "id": "dashboard-abc123",
  "name": "My Dashboard",  
  "type": "dashboard",
  "owner": "user-uuid",
  "version": 60,
  "modificationInfo": {...},
  "content": {
    "version": 21,
    "variables": [],
    "tiles": {...},
    "layouts": {...}
  }
}

Metadata (top-level):

• .id - Document ID
• .name - Dashboard name
• .owner - Owner UUID
• .version - Document version (change tracking)
• .modificationInfo - Creation/modification timestamps

Dashboard content (.content):

• .content.version - Dashboard schema version (current: 21)
• .content.tiles - Tile definitions
• .content.layouts - Tile positioning
• .content.variables - Dashboard variables

All jq examples in this skill use the .content.* paths.

---

When to Load References

This skill uses progressive disclosure - load only what you need:

• Start here: SKILL.md provides core concepts and quick-start examples
• Load references on-demand: Each reference file covers a specific deep-dive topic
• Context efficiency: Progressive loading enables task completion without external documentation