Dynatrace

io.github.Dynatrace由 GitHub 账号 Dynatrace 发布v10.0.0更新于 Nov 3, 2026

将 AI 助手连接到 Dynatrace，以查询可观测性数据并分析问题。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

Connect AI assistants to Dynatrace to query observability data and analyze problems.

已验证Streamable HTTP可网页运行云端与基础设施安全与监控数据与分析

概览

Dynatrace 的托管 MCP 服务（{environment_id}.apps.dynatrace.com）；需要 API 密钥；Streamable HTTP。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

端点
{environment_id}.apps.dynatrace.com

安装

在 SourceWeft 中

  1. 打开 控制台中的 Dynatrace，将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Dynatrace for AI

[OpenSSF Scorecard]

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)

bash
npx skills add dynatrace/dynatrace-for-ai

Works with Claude Code, Cursor, Cline, GitHub Copilot, OpenCode, and other compatible agents.

Claude Code Plugin

bash
claude plugin install dynatrace@claude-plugins-official

Prefer browsing interactively? Run /plugin in Claude Code, open the Discover tab, and search "Dynatrace".

The plugin includes skills as well as the Dynatrace MCP server. Set these environment variables before starting Claude Code to connect it to your environment:

bash
export DT_ENVIRONMENT=https://<env>.apps.dynatrace.com   # e.g. https://abc12345.apps.dynatrace.comexport DT_PLATFORM_TOKEN=<your-platform-token>

Verify that it works via:

bash
claude mcp login plugin:dynatrace:dynatrace

Please consult the Dynatrace MCP server docs for a full list of scopes required for using the MCP Server with a Platform Token.

To update the plugin, use:

bash
claude plugin marketplace updateclaude plugin update dynatrace@claude-plugins-official

Note: The bundled MCP server connects to your Dynatrace environment. See the Dynatrace Privacy Policy for details on data handling.

Cursor Plugin

The Dynatrace plugin is listed on the Cursor Marketplace. Install is GUI-only: open Customize in the Cursor sidebar, find "Dynatrace", select Install, and choose project or user scope.

Set the same DT_ENVIRONMENT and DT_PLATFORM_TOKEN environment variables shown above before starting Cursor.

Google Antigravity Plugin

Install the plugin with the Antigravity CLI:

bash
agy plugin install https://github.com/Dynatrace/dynatrace-for-ai

In the Antigravity CLI you can also run /plugin install https://github.com/Dynatrace/dynatrace-for-ai.

The plugin includes all skills and the Dynatrace MCP server. It stays disabled until you configure the MCP server. Open /plugin, select dynatrace, and turn it on. Then enter:

  • DT_ENVIRONMENT: your environment URL, e.g. https://abc12345.apps.dynatrace.com (https:// is required; leave off the trailing slash)
  • DT_PLATFORM_TOKEN: a platform token with the MCP gateway scopes

You can change these values later from Configure MCP servers... in /plugin. Antigravity does not read them from your shell environment.

Devin Plugin

The Dynatrace plugin is listed on the Devin Marketplace. Install via the Devin CLI:

bash
devin plugins install CognitionAI/devin-marketplace#plugins/dynatrace

Or from the Devin web app: Customize → Plugins → Add plugin → From repository.

Enter your Dynatrace environment host and a platform token with the MCP gateway scopes when prompted. Skills ship bundled with the plugin; the listing is maintained directly in Cognition's repo, synced from this one.

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.

bash
brew install dynatrace-oss/tap/dtctl                        # Installdtctl auth login --context my-env \  --environment "https://<env>.apps.dynatrace.com"           # Authenticatenpx skills add dynatrace-oss/dtctl                           # Install the dtctl skilldtctl 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.

The MCP server is remote — Dynatrace hosts it, so there is nothing to install. Releases are published to the official MCP registry as io.github.Dynatrace/dynatrace-for-ai, so MCP hosts that read the registry can add it by name.

Skills

DQL & Query Language

SkillDescription
dt-dql-essentialsDQL syntax rules, common pitfalls, and query patterns. Load this before writing any DQL.

Observability

SkillDescription
dt-obs-servicesService RED metrics and runtime telemetry for .NET, Java, Node.js, Python, PHP, and Go.
dt-obs-frontendsReal User Monitoring, Web Vitals, user sessions, mobile crashes, and frontend errors.
dt-obs-tracingDistributed traces, spans, service dependencies, and failure detection.
dt-obs-hostsHost and process metrics: CPU, memory, disk, network, and containers.
dt-obs-kubernetesKubernetes clusters, pods, nodes, workloads, labels, and resource relationships.
dt-obs-awsAWS resources: EC2, RDS, Lambda, ECS/EKS, VPC, load balancers, and cost optimization.
dt-obs-azureAzure resources: VMs, VMSS, SQL Database, Storage, AKS, App Service, Functions, VNet, Event Hubs, Container Apps, and Key Vault.
dt-obs-gcpGCP resources: Compute Engine, GKE, Cloud Run, Pub/Sub, VPC, DNS, IAM, and Secret Manager.
dt-obs-logsLog queries, filtering, pattern analysis, and log correlation.
dt-obs-problemsProblem entities, root cause analysis, impact assessment, and problem correlation.
dt-obs-predictive-analyticsTime series forecasting, capacity saturation planning, and trend/anomaly detection across hosts, services, and infrastructure.
dt-alertingEnd-to-end alerting lifecycle: anomaly detector setup, alert events in Grail, problem grouping, and workflow notification routing.
dt-obs-analyticsAnalyze Dynatrace dashboards and notebooks with Davis analyzers: anomaly detection, novelty scoring, and metric correlation.
dt-obs-ext-monitorsIngest third-party test and monitor results into Dynatrace Grail via the platform events ingest API.
dt-obs-extensionsCheck Dynatrace extension status and troubleshoot extension errors: monitoring configuration status, error diagnosis, and error code interpretation.
dt-obs-genaiAnalyze observability signals from GenAI applications: golden signals, LLM cost/token analytics, agent tool-call behavior, and evaluation results.
dt-obs-log-semantic-mappingSuggest and validate semantic dictionary mappings for audit log integrations, using vendor log payloads or live ingested events.
dt-obs-network-devicesAnalyze SNMP-monitored network devices (switches, routers, firewalls, load balancers): topology, interface metrics, and SNMP trap/syslog events.
dt-obs-network-flowsAnalyze network flows from OneAgent, NetFlow/IPFIX/sFlow, and cloud VPC flow logs: top talkers, communication dependencies, and connection health.

Security

SkillDescription
dt-sec-insightsQuery and analyze security data in security.events: Runtime Vulnerability Analytics, Runtime Application Protection, Automated Detections (MITRE ATT&CK), and Security Posture Management (KSPM/CSPM).
dt-sec-contextualizationResolve security signals and IoC matches to runtime entities, and connect findings across topology levels through a shared runtime entity.
dt-sec-ioc-huntingHunt threat-intelligence indicators of compromise across logs and spans, producing a threat-exposure score.
dt-sec-semantic-mappingSuggest and validate semantic dictionary mappings for new security integrations, using vendor API samples or live events.
dt-obs-compliance-assistantMonitor and investigate EU DORA compliance posture: compliance score, Critical/Important Function (CIF) health, incident classification, and ICT risk inputs.

Instrumentation Setup

SkillDescription
dt-setup-oneagentReference for installing Dynatrace OneAgent across VMs, Kubernetes, AWS Lambda, Windows hosts, remote EC2 instances, and Azure VMs/VMSS.
dt-setup-androidInstrument an existing Android project (Kotlin or Java) with the Dynatrace Mobile Agent: Gradle plugin, agent config, and user privacy opt-in.
dt-setup-flutterIntegrate the Dynatrace Flutter Plugin: dependency setup, config, SDK bootstrap, navigation tracking, and verification.
dt-setup-iosSet up the Dynatrace iOS SDK via Swift Package Manager: SPM dependency, Dynatrace.plist config, privacy opt-in, and Xcode build verification.
dt-setup-react-nativeIntegrate the Dynatrace React Native Plugin for bare React Native and Expo: dependency setup, dynatrace.config.js, Babel registration, navigation tracking, and verification.
dt-setup-genaiInstrument a GenAI/LLM app (Python or TypeScript, any provider or agent SDK) to emit OpenTelemetry gen_ai.* spans queryable in Dynatrace: detect, instrument, enrich, validate.
dt-setup-openinference-migrationMigrate a GenAI/LLM app from Traceloop/OpenLLMetry to OpenInference with gen_ai.* semantic conventions enabled, including ingestion shape and cardinality trade-offs.

Platform

SkillDescription
dt-app-dashboardsCreate, modify, and analyze Dynatrace dashboards: tiles, layouts, variables, and visualizations.
dt-app-notebooksCreate, modify, and analyze Dynatrace notebooks: sections, DQL queries, and analytics workflows.
dt-js-runtimeDynatrace server-side JavaScript runtime: function contract, runtime limits, Web APIs, Node.js modules, and the @dynatrace-sdk/* catalog.
dt-platform-costsQuery 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

SkillDescription
dt-migrationMigrate classic entity-based DQL and topology navigation to Smartscape equivalents.
dt-upgradeGuide an upgrade from classic/2nd-gen to 3rd-gen Dynatrace: tenant readiness, migration actions per feature area, and AWS/Azure/GCP cloud integration cutover to Smartscape on Grail.

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.

PromptDescription
dt-daily-standupGenerate a daily standup report for one or more services.
dt-health-checkCheck the health of a service in production.
dt-incident-responseRespond to an active production incident with triage, root cause, and a shareable report.
dt-investigate-errorInvestigate recent errors using Davis Problems as the entry point (problems → logs → traces).
dt-performance-regressionAnalyze whether a recent deployment caused a performance regression.
dt-troubleshoot-problemTroubleshoot an existing Dynatrace problem with structured log and trace investigation.

How Skills Work

Skills follow the Agent Skills specification and use progressive disclosure:

  1. Catalog - Agents load only name + description (~100 tokens per skill) to know what's available.
  2. Instructions - When relevant, the full SKILL.md is loaded (<5000 tokens).
  3. 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

来源：README.md，提交 5fafa6b

工具

0
该服务器需要 API 密钥等凭据，因此 SourceWeft 无法在没有凭据的情况下读取其工具，也未收录。

版本历史

2
  1. v10.0.0最新Nov 3, 2026
  2. v7.0.0Sep 16, 2026

评分

已满足适用检查项的 60%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分