What prerequisites do I need?
You need a Dynatrace UFO device on your network. Find its IP address (check your router or try `ufo.local` if mDNS is available).
@rhoegg
基本情報
MCP server for Dynatrace UFO
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": {
"ufo-mcp-server": {
"command": "docker",
"args": [
"pull",
"starspace46/ufo-mcp:latest"
]
}
}
}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。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A server that enables controlling a Dynatrace UFO device through MCP-compatible clients like Claude Desktop. It supports multi-agent coordination via a Desktop Extension and offers tools to set lighting, play effects, and query state.
Install via direct download, Docker, or build from source. Configure the UFO IP address via the --ufo-ip flag or UFO_IP environment variable. For single‑agent use, add a direct MCP configuration to your client (e.g., Claude Desktop or Cline). For multi‑agent coordination, build and install the Desktop Extension. Once configured, ask your client to perform actions like “turn the UFO red” or “play the rainbow effect.”
You need a Dynatrace UFO device on your network. Find its IP address (check your router or try `ufo.local` if mDNS is available).
Download the appropriate binary for your OS (macOS Apple Silicon, macOS Intel, or Linux) and make it executable. Alternatively, use Docker (`docker pull starspace46/ufo-mcp:latest`) or build from source with Go.
Yes—use the Desktop Extension (build with `make dxt` and run the HTTP server). This allows multiple Claude instances to share the same UFO state and coordinate in real time.
The server supports stdio (for desktop clients like Claude and Cline), HTTP/2+SSE (for web-based clients), and legacy SSE (for MuleSoft Anypoint Code Builder).
If the server cannot find the UFO, verify the IP address in your router’s admin panel. Ensure the UFO is powered on and connected to the same network. For effects not saving, check write permissions on the effects file location.
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns

Model Context Protocol Servers

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.
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
コメント