広告掲載
MCP.so
ログイン

Dynatrace MCP Server

@dynatrace-oss

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

dynatrace-oss

Dynatrace MCP Server について

MCP server for Dynatrace Observability

#monitoring#mcp#dynatrace#copilot#observability#cline#claude

Dynatrace MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "dynatrace-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@dynatrace-oss/dynatrace-mcp-server@latest",
        "--help"
      ]
    }
  }
}

Dynatrace MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Dynatrace MCP Server?

The Dynatrace MCP Server is a local Model Context Protocol server that allows AI Assistants to interact with the Dynatrace observability platform, bringing real-time observability data directly into your development workflow. It targets developers and DevOps teams using MCP-compatible clients (e.g., VS Code, Claude, Cursor, GitHub Copilot, ChatGPT). Note: This product is not officially supported by Dynatrace and is currently in Maintenance Mode.

How to use Dynatrace MCP Server?

Install via npx -y @dynatrace-oss/dynatrace-mcp-server (type: stdio). Configure the DT_ENVIRONMENT environment variable with your Dynatrace Platform URL (e.g., https://abc12345.apps.dynatrace.com). Authentication uses OAuth Authorization Code Flow in your browser; tokens are stored in the OS keychain. For headless environments, set DT_MCP_TOKEN_STORAGE=file to persist tokens in ~/.config/dynatrace-mcp/.

Key features of Dynatrace MCP Server

  • Observability & problem management (list_problems, list_vulnerabilities, etc.)
  • Query Dynatrace Grail data via natural language or DQL
  • Entity discovery (find_entity_by_name)
  • Dynatrace Intelligence integration (chat with Davis Copilot)
  • Automation and notifications (Slack, email, events)
  • Create Dynatrace Notebooks to share results

Use cases of Dynatrace MCP Server

  • Real-time observability for early detection and proactive monitoring
  • Contextual debugging with full context from exceptions, logs, and anomalies
  • Security insights with vulnerability analysis and problem tracking
  • Natural language queries using AI-powered DQL generation
  • Multi-phase incident investigation with automated impact assessment

よくある質問

1

What are the prerequisites?

Node.js v24 or newer is required to run the Dynatrace MCP Server. You also need a Dynatrace Platform URL (classic URLs like `abc12345.live.dynatrace.com` are not supported).

2

How does authentication work?

Authentication is handled via OAuth Authorization Code Flow in your browser. Tokens are securely stored in the OS keychain (macOS Keychain, Windows Credential Manager, or Linux Secret Service) and reused on subsequent starts. The browser only opens once per token lifetime. In headless environments, set `DT_MCP_TOKEN_STORAGE=file` to persist tokens.

3

Are there any costs associated with using this server?

The server is free, but using certain capabilities (notably `execute_dql` and queries to Dynatrace Grail) may incur costs based on your Dynatrace consumption model (GB scanned). The server includes built-in budget tracking via `DT_GRAIL_QUERY_BUDGET_GB` (default 1000 GB) and warns when approaching 80% of the budget.

4

Can I use this in a container or headless environment?

Yes. You must set `DT_MCP_TOKEN_STORAGE=file` to persist OAuth tokens in a file (`~/.config/dynatrace-mcp/`) instead of the OS keychain, which is unavailable in headless/container environments.

5

Is there a remote alternative that doesn't require local setup?

Yes. Dynatrace offers a Remote Dynatrace MCP Server (available from the Dynatrace Hub) that requires no local setup and connects instantly to your Dynatrace environment from any MCP-compatible client. A migration guide is provided in the repository.

コメント

「その他」の他のコンテンツ

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
広告掲載