Dynatrace for AI
Everything AI agents need to work with Dynatrace, starting with skills.
Skills are portable knowledge packages following the Agent Skills open format. They give AI coding agents the domain-specific context to query, analyze, and interpret Dynatrace data. They work with Claude Code, GitHub Copilot, Cursor, OpenCode, Gemini CLI, and 30+ other compatible tools.
Installation
Skills Package (skills.sh)
npx skills add dynatrace/dynatrace-for-ai
Works with Claude Code, Cursor, Cline, GitHub Copilot, OpenCode, and other compatible agents.
Claude Code Plugin
claude plugin marketplace add dynatrace/dynatrace-for-ai
claude plugin install dynatrace@dynatrace-for-ai
The plugin includes the Dynatrace MCP server. Set these environment variables before starting Claude Code to connect it to your environment:
export DT_ENVIRONMENT=https://<env>.apps.dynatrace.com # e.g. https://abc12345.apps.dynatrace.com
export DT_PLATFORM_TOKEN=<your-platform-token>
Please consult the Dynatrace MCP server docs for a full list of scopes required for using the MCP Server with a Platform Token.
Update with claude plugin marketplace update && claude plugin update dynatrace@dynatrace-for-ai.
Manual
Copy skill directories into your agent's skills path (.agents/skills/, .claude/skills/, .cursor/skills/, etc.).
Connecting to Dynatrace
Skills provide knowledge only. To run live queries and manage your environment, pair them with a tool.
Dynatrace CLI (dtctl)
dtctl is a kubectl-style CLI for the Dynatrace platform. It ships with its own Agent Skill that teaches agents how to operate it.
brew install dynatrace-oss/tap/dtctl # Install
dtctl auth login --context my-env \
--environment "https://<env>.apps.dynatrace.com" # Authenticate
npx skills add dynatrace-oss/dtctl # Install the dtctl skill
dtctl doctor # Verify setup
Or install the dtctl skill with dtctl itself: dtctl skills install
Dynatrace MCP Server
The Dynatrace MCP server provides Dynatrace API access via MCP. The Claude Code plugin bundles the MCP server configuration automatically — just set DT_ENVIRONMENT and DT_PLATFORM_TOKEN as shown above. For other agents that support MCP natively, see the MCP server docs.
Skills
DQL & Query Language
| Skill | Description |
|---|---|
| dt-dql-essentials | DQL syntax rules, common pitfalls, and query patterns. Load this before writing any DQL. |
Observability
| Skill | Description |
|---|---|
| dt-obs-services | Service RED metrics and runtime telemetry for .NET, Java, Node.js, Python, PHP, and Go. |
| dt-obs-frontends | Real User Monitoring, Web Vitals, user sessions, mobile crashes, and frontend errors. |
| dt-obs-tracing | Distributed traces, spans, service dependencies, and failure detection. |
| dt-obs-hosts | Host and process metrics: CPU, memory, disk, network, and containers. |
| dt-obs-kubernetes | Kubernetes clusters, pods, nodes, workloads, labels, and resource relationships. |
| dt-obs-aws | AWS resources: EC2, RDS, Lambda, ECS/EKS, VPC, load balancers, and cost optimization. |
| dt-obs-azure | Azure resources: VMs, VMSS, SQL Database, Storage, AKS, App Service, Functions, VNet, Event Hubs, Container Apps, and Key Vault. |
| dt-obs-gcp | GCP resources: Compute Engine, GKE, Cloud Run, Pub/Sub, VPC, DNS, IAM, and Secret Manager. |
| dt-obs-logs | Log queries, filtering, pattern analysis, and log correlation. |
| dt-obs-problems | Problem entities, root cause analysis, impact assessment, and problem correlation. |
| dt-obs-predictive-analytics | Time series forecasting, capacity saturation planning, and trend/anomaly detection across hosts, services, and infrastructure. |
| dt-alerting | End-to-end alerting lifecycle: anomaly detector setup, alert events in Grail, problem grouping, and workflow notification routing. |
Security
| Skill | Description |
|---|---|
| dt-sec-insights | Query and analyze security data in security.events: Runtime Vulnerability Analytics, Runtime Application Protection, Automated Detections (MITRE ATT&CK), and Security Posture Management (KSPM/CSPM). |
Mobile Instrumentation
| Skill | Description |
|---|---|
| dt-obs-android | Instrument an existing Android project (Kotlin or Java) with the Dynatrace Mobile Agent: Gradle plugin, agent config, and user privacy opt-in. |
| dt-obs-flutter | Integrate the Dynatrace Flutter Plugin: dependency setup, config, SDK bootstrap, navigation tracking, and verification. |
| dt-obs-ios-sdk | Set up the Dynatrace iOS SDK via Swift Package Manager: SPM dependency, Dynatrace.plist config, privacy opt-in, and Xcode build verification. |
| dt-obs-react-native | Integrate the Dynatrace React Native Plugin for bare React Native and Expo: dependency setup, dynatrace.config.js, Babel registration, navigation tracking, and verification. |
Platform
| Skill | Description |
|---|---|
| dt-app-dashboards | Create, modify, and analyze Dynatrace dashboards: tiles, layouts, variables, and visualizations. |
| dt-app-notebooks | Create, modify, and analyze Dynatrace notebooks: sections, DQL queries, and analytics workflows. |
| dt-js-runtime | Dynatrace server-side JavaScript runtime: function contract, runtime limits, Web APIs, Node.js modules, and the @dynatrace-sdk/* catalog. |
| dt-platform-costs | Query and analyze a Dynatrace tenant's actual billing and usage data with DQL: DPS consumption breakdown, cost-normalized spend ranking, chargeback/showback, cost drivers, and entity-level cost drill-down. |
Migration
| Skill | Description |
|---|---|
| dt-migration | Migrate classic entity-based DQL and topology navigation to Smartscape equivalents. |
Prompts
Prompts are reusable task templates for common Dynatrace workflows. You can copy them from the /prompts/ directory and paste them directly into any AI chat. For VS Code/GitHub Copilot users, copy prompts into .github/prompts/ to use as slash commands (e.g. /troubleshoot-problem).
Each prompt references the relevant skills above — load those skills first for best results.
| Prompt | Description |
|---|---|
| dt-daily-standup | Generate a daily standup report for one or more services. |
| dt-health-check | Check the health of a service in production. |
| dt-incident-response | Respond to an active production incident with triage, root cause, and a shareable report. |
| dt-investigate-error | Investigate recent errors using Davis Problems as the entry point (problems → logs → traces). |
| dt-performance-regression | Analyze whether a recent deployment caused a performance regression. |
| dt-troubleshoot-problem | Troubleshoot an existing Dynatrace problem with structured log and trace investigation. |
How Skills Work
Skills follow the Agent Skills specification and use progressive disclosure:
- Catalog - Agents load only
name+description(~100 tokens per skill) to know what's available. - Instructions - When relevant, the full
SKILL.mdis loaded (<5000 tokens). - Resources - Detailed reference files in
references/are loaded on demand.
Install all skills without penalty. Agents only load what they need.
Contributing
Skill content (skills/) is maintained internally at Dynatrace and published here periodically. PRs that modify skill files will not be accepted — please open an issue instead to suggest changes. See CONTRIBUTING.md for details on what can be contributed directly.
License
Apache-2.0
No comments yet
Be the first to share your take.