
Lucius MCP
io.github.ivanostanin由 GitHub 帳號 ivanostanin 發布v0.17.0更新於 Nov 11, 2026
MCP server for managing Allure TestOps tests, launches, plans, defects, and metadata.
概覽
讓助理管理 Allure TestOps 中測試案例、啟動(launch)、測試計畫、缺陷與專案中繼資料的 MCP 伺服器。
- 可以做什麼
- 建立、更新、刪除與檢視測試案例、自訂欄位與測試分層
- 搜尋並列出測試案例、測試套件、整合與專案中繼資料
- 管理共用步驟與測試套件,包含連結與指派
- 建立與管理啟動、上傳測試結果、附加檔案、重跑及手動測試工作階段
- 管理測試計畫、缺陷與缺陷比對規則,並依案例產生特定框架的測試程式碼
- 適用情境
- 適合讓 AI 代理在既有的 Allure TestOps 專案中工作:草擬或整理測試文件、組織測試套件、處理缺陷,或檢視啟動結果,而不必手寫 API 呼叫。
- 執行需求
- 透過 uvx(Python 3.11-3.14)以 stdio 在本機執行,或使用 Claude Desktop 的 MCPB 套件。需要 ALLURE_ENDPOINT(Allure TestOps 基礎網址)、ALLURE_PROJECT_ID 以及密鑰 ALLURE_API_TOKEN;也可用 lucius auth 命令列儲存憑證。需要能連線至 Allure 執行個體的網路。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Lucius MCP,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
[PyPI Version] [PyPI Python Version] [PyPI Downloads] [GitHub License]
Allure TestOps MCP Server
Lucius is a specialized Model Context Protocol (MCP) server for Allure TestOps, built with FastMCP and Starlette.
🎯 Motivation
Allure TestOps is a powerful tool with a huge API. When you're using an AI agent to manage your tests, it can easily get lost in the details or fail because of a small technical mistake.
Lucius makes this easier by giving your AI tools that are simple to use and hard to break:
- Clear Tools: Every tool is designed for a specific task, like "finding a test case" or "updating a launch".
- Helpful Errors: If an AI makes a mistake, Lucius doesn't just return a code—it provides an "Agent Hint" that explains exactly what went wrong and how to fix it.
- Solid Foundation: We follow a clean "Thin Tool" structure, meaning the logic is consistent and easy for both humans and AI to follow.
🛠️ Supported Tools
See the full reference in Tool Reference.
🚀 Quick Start
- Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh - Setup Credentials: Create a
.envfile with the variables below, or save CLI auth withlucius auth. - Run Server:
uv run start
Basic .env for Quick Start
🔌 Claude Desktop Integration
The easiest way to use Lucius in Claude Desktop is via the .mcpb bundle:
- Download the latest
lucius-mcp.mcpbfrom Releases. - Open with Claude Desktop.
- Configure your Allure credentials in the UI.
💻 Claude Code Integration
To add Lucius to Claude Code, use the following command from within your project directory:
Project-scoped text config example (.mcp.json):
🧠 Codex Integration
To add Lucius to Codex (CLI or IDE extension), use:
Text config example (~/.codex/config.toml or project .codex/config.toml):
For detailed setup, including Claude Desktop (MCPB) integration, see Setup Guide.
🐍 Supported Python versions
Lucius supports Python 3.11 through 3.14 for runtime use. The generated MCPB manifests and the representative Nuitka CLI compiler matrix validate the same range. Python 3.15 support is experimental: installation may require source builds, and platform compatibility is still being verified. See the development guide for current limitations. Python 3.10 remains unsupported because the locked filelock security update requires Python 3.11 or newer.
💻 Command-Line Interface (CLI)
Lucius also provides a universal CLI entry point for direct tool execution from the command line:
CLI Features:
- 🎯 Type-safe entity/action invocation with validation
- 🔐 Optional persistent CLI auth with native per-user config storage
- 📊 Multiple output formats (JSON, table, csv, plain)
- 🔍 Per-action help with parameters and examples
- 🛡️ Clean error messages with guidance
- 📦 Standalone binaries for Linux, macOS, and Windows
CLI auth precedence is:
- Explicit tool args such as
api_tokenorproject_id - Environment variables
- Saved CLI auth config from
uv run lucius auth - Defaults
Saved CLI auth uses native config locations:
- Linux/Unix:
$XDG_CONFIG_HOME/lucius/auth.jsonor~/.config/lucius/auth.json - macOS:
~/Library/Application Support/lucius/auth.jsonunless XDG overrides are explicitly set - Windows:
%LOCALAPPDATA%\lucius\auth.json
For full CLI documentation and installation instructions, see CLI Guide.
📡 Telemetry
Lucius collects privacy-preserving usage telemetry to improve tool quality. Telemetry is enabled by default and sends metadata
to https://stats.ostanin.me, an endpoint operated by the project owner (no third party has access to this endpoint).
If this is acceptable in your environment, staying opted in helps improve Lucius over time. If you want to opt out, set
TELEMETRY_ENABLED=false in your environment.
No API tokens, test content, or tool arguments are sent.
See Telemetry & Privacy for the full data dictionary and telemetry behavior details.
📂 Documentation
Full documentation is available in the docs/ folder:
- Architecture & Design
- Tool Reference
- Configuration & Setup
- Telemetry & Privacy
- Attachment download capability links
- Development Guide
- AI Agent Protocol
🤝 Contributing
Contributions are welcome! Please see the Contribution Guidelines and the Development Guide for more details.
來源:README.md,提交 a649efa
工具
0版本歷史
12- v0.17.0最新Nov 11, 2026
- v0.16.9Nov 5, 2026
- v0.16.8Nov 3, 2026
- v0.16.6Oct 21, 2026
- v0.16.5Oct 12, 2026
- v0.16.4Oct 6, 2026
- v0.16.3Oct 1, 2026
- v0.16.2Sep 29, 2026
- v0.16.1Sep 23, 2026
- v0.15.7Sep 21, 2026
- v0.15.6Sep 17, 2026
- v0.15.5Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分