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.
README
Harmonica MCP Server
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
- Sign up for Harmonica (free)
- Go to Profile > API Keys > Generate API Key
- 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.