daofy — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by chinawsb · MCP Server · ★ 107

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is daofy safe to install? View the security audit →

About daofy

Daofy for Delphi 一个为 AI 助手(如 Claude Desktop、CodeArts Agent 等)提供 Delphi 工程编译能力和知识库查询功能的 MCP Server。如果您觉得有用,请不要吝啬您的 Star! ⭐ Daofy(道飞)——为创意插上翅膀。 项目简介 Daofy for Delphi 是一个基于 Model Context Protocol (MCP) 的 MCP Server,它允许 AI 助手直接编译 Delphi 项目并查询 Delphi 知识库。通过这个工具,您可以在与 AI 助手的对话中直接编译 Delphi 工程、查询 API 文档、搜索代码示例,无需手动切换到 IDE 或命令行。 主要优势: 无缝集成到 AI 助手工作流中 自动检测和配置 Delphi 编译器 内置 Delphi 源码知识库,支持语义搜索 项目级知识库,自动追踪三方库和项目源码 通用文档知识库支持 Delphi CHM 帮助文档全文搜索 支持所有主流 AI 助手平台 完整的编译事件支持 详细的错误诊断和日志 功能特性 编译功能 工程整体编译: 支持编译完整的 Delphi 工程(.dproj/.dpr),生成可执行文件或动态链接库 MSBuild 编译: 优先使用 MSBuild 编译,自动处理依赖关系和编译事件 单文件编译: 支持编译单个 Delphi 单元文件(.pas),进行语法检查 自动检测编译器: 自动从注册表检测已安装的 Delphi 编译器,无需手动配置 智能库路径解析: 自动分析项目依赖,智能选择需要的第三方库路径,避免命令行过长 编译事件支持: 支持 PreBuildEvent、PostBuildEvent、PreLinkEvent,包含完整的参数替换 命令行参数生成: 支持生成 Delphi 编译器命令行参数,便于调试和预览 编译器配置管理: 支持配置和管理多个 Delphi 编译器版本 环境检查: 提供编译器环境状态检查功能 丰富的编译选项: 支持条件编译符号、搜索路径、优化选项、调试信息、警告控制等 知识库功能 Delphi 源码知识库: 内置 Delphi 官方源码知识库,支持类、函数搜索和语义搜索 项目知识库: 为每个项目构建独立知识库,自动追踪三方库和项目源码 三方库知识库: 从 .dproj 文件自动提取三方库路径并构建知识库 增量更新: 自动检测源码变动,增量更新项目知识库 通用文档知识库: 支持 txt/md/html/docx/doc/pdf/epub/hlp/chm 和网页文档的扫描与搜索 必需依赖: be

ai-assistantclaude-desktopcodeartscodeartsdaofydelphidelphi-compilerdelphi-ideembarcaderomcpmodel-context-protocol

Quick Facts

Stars107
Forks20
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score62.0172632596648/100
Open Issues2
Last Updated2026-09-16
Created2026-03-10
Platformsclaude-code, mcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with daofy for enhanced workflows:

daofy alternative? Top 6 similar tools

Looking for a daofy alternative? If you're comparing daofy with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-server-tree-sitter by wrale · ⭐ 309

    MCP Server for Tree-sitter

  • mcp-dock by OldJii · ⭐ 228

    MCP Server & Config Manager for 14 AI Clients — Cursor, VS Code, Claude Code, Gemini CLI, Windsurf, Zed, TRAE,

  • opencode-browser by michaljach · ⭐ 82

    Browser automation plugin for OpenCode AI editor - Control Chrome/Edge with AI, automate web testing, scraping

  • mcp-gearbox by rohitsoni007 · ⭐ 62

    A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

  • roam-code by Cranot · ⭐ 517

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • mcp-server-bash-sdk by muthuishere · ⭐ 515

    MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime de

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is daofy?

daofy is Daofy for Delphi — MCP Server that compiles Delphi projects and queries knowledge base for AI assistants.. It is categorized as a MCP Server with 107 GitHub stars.

What programming language is daofy written in?

daofy is primarily written in Python. It covers topics such as ai-assistant, claude-desktopcodearts, codearts.

How do I install or use daofy?

You can find installation instructions and usage details in the daofy GitHub repository at github.com/chinawsb/daofy. The project has 107 stars and 20 forks, indicating an active community.

What license does daofy use?

daofy is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to daofy?

The top alternatives to daofy on Agent Skills Hub include mcp-server-tree-sitter, mcp-dock, opencode-browser. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools