Roundtable
Generates automated meeting minutes and discussion summaries in Markdown format for structured documentation of roundtable sessions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RoundtableOrganize a debate between the Architect and Product Manager about our tech stack"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
圆桌会议系统 (Roundtable)
多角色 AI 讨论系统,通过定义不同角色让多个 AI 代表不同观点进行讨论,最终形成共识决策。
功能特性
角色管理 - 创建、删除角色,每个角色有独立的 IDENTITY.md 定义
圆桌讨论 - 多角色轮流发言,自动检测共识达成
会议纪要 - 自动生成 Markdown 格式会议纪要
时间感知 - 支持时间相关话题的实时搜索
MCP 集成 - 支持通过 MCP 协议调用所有功能
Related MCP server: consensus-mcp
快速开始
1. 克隆项目
git clone https://github.com/your-repo/roundtable-mcp.git
cd roundtable2. 安装依赖
pip install -r requirements.txt3. 配置
# 复制配置模板
cp config.json.example config.json
# 编辑配置,填入你的 API Key
vim config.json4. 启动
python3 main.pyMCP 部署
与 Claude Code 集成
在 Claude Code 配置文件中添加:
{
"mcpServers": {
"Roundtable": {
"command": "/path/to/roundtable/venv/bin/python",
"args": ["/path/to/roundtable/mcp_server.py"]
}
}
}MCP 工具列表
工具 | 说明 |
list_roles | 列出所有角色 |
get_role_identity | 获取角色 IDENTITY |
create_role | 创建角色 |
delete_role | 删除角色 |
list_meetings | 列出所有会议 |
create_meeting | 创建会议 |
get_meeting | 获取会议信息 |
get_meeting_minutes | 获取会议纪要 |
delete_meeting | 删除会议 |
update_meeting_topic | 更新主题 |
add_meeting_participant | 添加参与者 |
remove_meeting_participant | 删除参与者 |
get_meeting_status | 获取状态 |
update_meeting_rounds | 更新轮次 |
start_meeting | 启动会议 |
目录结构
roundtable/
├── main.py # 入口文件
├── cli.py # 命令行界面
├── config_manager.py # 配置管理
├── role_manager.py # 角色管理
├── meeting_manager.py # 会议管理
├── llm_client.py # LLM 调用
├── mcp_server.py # MCP 服务器
├── config.json.example # 配置模板
├── mcp.json.example # MCP 配置模板
└── requirements.txt # 依赖依赖
Python >= 3.8
anthropic >= 0.83.0
许可证
GPL-3.0 license
This server cannot be deployed
Maintenance
Related MCP Connectors
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Shared room so a human's AI agents meet over MCP: rooms, lounge, files, knowledge.
MCP-native collaborative markdown editor with real-time AI document editing
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables collaborative debates between multiple AI agents, allowing them to discuss and reach consensus on user prompts.1MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables multi-model debate and consensus building through a single tool. It orchestrates multiple AI models from various providers to debate topics and reach validated conclusions with real-time progress tracking.6 npm3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AI agents to conduct multi-LLM roundtable discussions, returning structured common, divergent, and unique perspectives.MIT
- AlicenseAqualityCmaintenanceA multi-user AI group chat server via MCP that lets multiple users' AI agents join a shared discussion room to debate topics and reach convergence.710 npm10MIT