MCP server enabling AI expert debates - Dynamic expert generation for personalized multi-round philosophical discussions on any topic
Until 2026-09-25 this record combined several servers published from one repository. The others now have records of their own: iflow-mcp_guru-pk-mcp. Checks from before that date include them.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"guru-pk-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Guru-PK MCP 智能专家辩论系统 基于本地MCP(Model Context Protocol)的AI专家辩论系统,采用**动态专家生成架构**,根据问题而智能的创建最适合的专家组合进行多轮智慧碰撞。 ## ✨ 核心特色 - 🏭 **动态专家生成** - 完全问题驱动,每次生成专属专家组合 - 🌟 **无限专家池** - 突破固定专家限制,支持任意领域的专家生成 - 🔄 **多轮PK流程** - 独立思考 → 交叉辩论 → 最终立场 → 智慧综合 - 🎨 **塔夫特风格信息图** - 将专家辩论转化为严格遵循数据可视化大师爱德华·塔夫特设计原则的单页动态信息图 - 🤖 **智能分工架构** - MCP Host端LLM负责智能分析,MCP Server端提供流程指导 ## 🌐 在线演示 **👉 [查看信息图演示](https://mitsudoai.github.io/guru-pk-mcp/)** 这个网页展示了使用本MCP工具创建的塔夫特风格动态信息图,直观展现了专家辩论系统的强大功能。 ## 🚀 快速安装 ### 1. 安装依赖 **方式一:使用安装脚本(推荐)** **macOS/Linux:** ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` **Windows:** ```powershell powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" ``` **方式二:使用 pip 安装(适用于所有平台)** ```bash pip install uv ``` **方式三:下载安装包** 从 [UV Releases](https://github.com/astral-sh/uv/releases) 页面下载对应平台的安装包 ### 2. 配置MCP客户端 **推荐方式:从PyPI安装** ```json { "mcpServers": { "guru-pk": { "command": "uvx", "args": ["--from", "guru-pk-mcp", "guru-pk-mcp-server"], "env": { "DATA_DIR": "~/.guru-pk-data" // macOS/Linux: ~/目录, Windows: %USERPROFILE%目录 } } } } ``` > **更新说明**: > > - 当需要更新`guru-pk-mcp`到最新版本时,请执行命令: > > ```bash > uvx pip install --upgrade guru-pk-mcp > ``` > > - 此命令会从PyPI获取并安装最新发布的版本 > - 如果遇到缓存问题,可以强制刷新: > > ```bash > uvx --refresh-package guru-pk-mcp --from guru-pk-mcp python -c "print('✅ UVX缓存已刷新')" > ``` > > **注意**: > > - macOS用户可能需要使用完整路径:`/Users/{用户名}/.local/bin/uvx` > - Windows用户:`~`会自动解析为用户主目录(如 `C:\Users\{用户名}`),无需手动修改 **开发方式:从源码安装** ```json { "mcpServers": { "guru-pk": { "command": "uvx", "args": ["--from", "/path/to/guru-pk-mcp", "guru-pk-mcp-server"], "env": { "DATA_DIR": "~/.guru-pk-data" // macOS/Linux: ~/目录, Windows: %USERPROFILE%目录 } } } } ``` > **本地开发说明**: > > - 对于本地开发场景,如需刷新uvx缓存,请使用`make refresh-uvx` > - 此命令强制UVX重新安装本地包,确保使用最新的代码更改 ## 使用入门 重启MCP客户端,输入 `guru_pk_help` 获取帮助,或直接提问开始专家辩论! ```javascript // 1…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.