harmonica-mcp

harmonica-mcp

MCP server enabling AI agents to create and query Harmonica deliberation sessions. It allows users to create sessions, collect responses, and get summaries via natural language.

Category
访问服务器

README

Harmonica MCP Server

npm version

MCP server enabling AI agents to create and query Harmonica deliberation sessions.

Harmonica is a structured deliberation platform where groups coordinate through AI-facilitated async conversations. Create a session with a topic and goal, share a link with participants, and each person has a private 1:1 conversation with an AI facilitator. Responses are synthesized into actionable insights. Learn more.

Quick Start

1. Get an API key

  1. Sign up for Harmonica (free)
  2. Go to Profile > API Keys > Generate API Key
  3. Copy your hm_live_... key — it's only shown once

2. Configure your MCP client

Add to your MCP client config (e.g. Claude Code, Cursor, Windsurf):

{
  "mcpServers": {
    "harmonica": {
      "command": "npx",
      "args": ["-y", "harmonica-mcp"],
      "env": {
        "HARMONICA_API_KEY": "hm_live_your_key_here"
      }
    }
  }
}

3. Start a deliberation

Ask your AI agent to create a session:

Create a Harmonica session about "Team Retrospective" with the goal "Review Q1 and identify improvements"

Share the join URL with participants. Once they've responded, use get_responses and get_summary to see the results.

Tools

Tool Description
create_session Create a new deliberation session and get a shareable join URL (optional: questions)
update_session Update session metadata (topic, goal, context, critical, prompt)
list_sessions List your deliberation sessions (filter by status, search)
get_session Get full session details (includes facilitation prompt)
get_questions Get pre-session questions (data collection form)
get_responses Get participant responses
get_summary Get AI-generated summary
search_sessions Search by topic or goal
list_telegram_groups List Telegram groups registered to the user's account (no parameters)
install_method_spec Install an OFL method spec (method.md) as a runnable chain template

From Source

git clone https://github.com/harmonicabot/harmonica-mcp.git
cd harmonica-mcp
npm install && npm run build

Then use node /path/to/harmonica-mcp/dist/index.js instead of npx -y harmonica-mcp in your config.

Environment Variables

Variable Required Default Description
HARMONICA_API_KEY Yes Your Harmonica API key
HARMONICA_API_URL No https://app.harmonica.chat API base URL

Roadmap

  • [ ] One-command install via npx add-mcp (auto-detects Claude Code, Cursor, Windsurf)
  • [ ] HTTP transport — zero-install setup, just add a URL
  • [ ] Inbound context — feed external data into sessions via MCP
  • [ ] Session templates discovery tool
  • [ ] TypeScript and Python client SDKs

See Also

  • harmonica-chat — Conversational Harmonica companion for Claude Code — design, create, and manage sessions (/harmonica-chat)
  • Harmonica docs — Full platform documentation and API reference

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选