What dependencies are required?
Go 1.23+ or a pre-built binary from the releases page.
@pyworkload
基本情報
MCP server for 3x-ui — an Xray/V2Ray proxy management panel. Exposes the 3x-ui HTTP API as MCP tools so LLMs can manage inbounds, clients, routing rules, Xray service, and server settings.
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": {
"3x-ui": {
"command": "go",
"args": [
"run",
"github.com/pyworkload/3x-ui-mcp/cmd/xui-mcp@latest"
],
"env": {
"XUI_HOST": "http://localhost:2053",
"XUI_USERNAME": "<your-username>",
"XUI_PASSWORD": "<your-password>"
}
}
}
}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。
An MCP server that exposes the 3x-ui (Xray/V2Ray proxy management panel) HTTP API as MCP tools, enabling LLMs to manage inbounds, clients, routing rules, Xray service, and server settings.
Add the server to your MCP config (claude_desktop_config.json or .mcp.json) with the go run command or a pre-built binary, and set the required environment variables: XUI_HOST, XUI_USERNAME, XUI_PASSWORD. Requires Go 1.23+ if using go run.
Go 1.23+ or a pre-built binary from the releases page.
Via environment variables: required `XUI_HOST`, `XUI_USERNAME`, `XUI_PASSWORD`, and optional `XUI_BASE_PATH` and `XUI_LOG_LEVEL`.
Stdio transport.
Uses the provided admin username and password for session management with automatic re-authentication.
The README does not specify limitations.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Hindsight: Agent Memory That Learns

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.
コメント