Reachy Mini MCP
Enables control of Pollen Robotics Reachy Mini robot through high-level emotional expressions and low-level motor commands, with support for vision, audio, and text-to-speech capabilities.
README
Reachy Mini MCP
Give your AI a body.
This MCP server lets AI systems control Pollen Robotics' Reachy Mini robot—speak, listen, see, and express emotions through physical movement. Works with Claude, GPT, Grok, or any MCP-compatible AI.
7 tools. 30 minutes to first demo. Zero robotics expertise required.
For AI Systems
Token-efficient tool reference for programmatic use:
| Tool | Args | Purpose |
|---|---|---|
speak |
text, listen_after=0 |
Voice + gesture, optionally listen after |
listen |
duration=3 |
STT via Deepgram Nova-2 |
snap |
- | Camera capture (base64 JPEG) |
show |
emotion, move="" |
Express emotion or play recorded move |
look |
roll, pitch, yaw, z, duration |
Head positioning (degrees) |
rest |
mode="neutral" |
neutral / sleep / wake |
discover |
library="emotions" |
Find available recorded moves |
speak()
Supports embedded move markers for choreographed speech:
speak("[move:curious1] What's this? [move:surprised1] Oh wow!")
Moves fire right before their speech chunk. Use listen_after=5 to hear response.
show()
Built-in emotions (fast, local):
neutral, curious, uncertain, recognition, joy, thinking, listening, agreeing, disagreeing, sleepy, surprised, focused
Recorded moves (81 from Pollen):
show(move="loving1")
show(move="fear1")
show(move="serenity1")
Use discover() to see all available moves.
Quick Start
# Install
cd reachy-mini-mcp
poetry install
# Set API key (required for speak/listen)
export DEEPGRAM_API_KEY=your_key_here
# Start simulator daemon
mjpython -m reachy_mini.daemon.app.main --sim --scene minimal
# Run MCP server
poetry run python src/server.py
Architecture
AI (Claude/GPT/Grok) → MCP Server → SDK → Daemon → Robot/Simulator
7 tools following Miller's Law—fits in working memory.
Voice Providers
| Provider | Status | Use Case |
|---|---|---|
| Grok Voice | ✅ Supported | xAI's expressive voice (Eve, Ara, Leo, Rex, Sal) |
| Deepgram | ✅ Supported | TTS (Aura 2) + STT (Nova 2) |
Grok Voice is used automatically when XAI_API_KEY is set. Falls back to Deepgram otherwise.
MCP Config
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"reachy-mini": {
"command": "poetry",
"args": ["-C", "/path/to/reachy-mini-mcp", "run", "python", "src/server.py"],
"env": {
"DEEPGRAM_API_KEY": "your_key_here"
}
}
}
}
Claude Code
~/.claude.json:
{
"mcpServers": {
"reachy-mini": {
"command": "poetry",
"args": ["-C", "/path/to/reachy-mini-mcp", "run", "python", "src/server.py"],
"env": {
"DEEPGRAM_API_KEY": "your_key_here"
}
}
}
}
Environment Variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
XAI_API_KEY |
No | - | Grok Voice TTS (preferred) |
GROK_VOICE |
No | Eve |
Grok voice: Ara, Eve, Leo, Rex, Sal, Mika, Valentin |
DEEPGRAM_API_KEY |
Yes* | - | TTS (fallback) + STT |
REACHY_DAEMON_URL |
No | http://localhost:8321/api |
Daemon API endpoint |
*Required if XAI_API_KEY not set
Requirements
- Python 3.10+
- reachy-mini SDK (installed via poetry)
- MuJoCo (for simulation)
- Deepgram API key (for speak/listen)
Hardware Notes
- Simulator:
mjpythonrequired on macOS for MuJoCo visualization - Real hardware: Same MCP server, daemon auto-connects
- Port conflicts: Zenoh uses 7447, daemon uses 8321 by default
License
MIT License - see LICENSE
Acknowledgments
- Reachy Mini SDK by Pollen Robotics (Apache 2.0)
- Grok Voice integration pattern from dillera's reachy_mini_conversation_app
Links
- Reachy Mini SDK (Apache 2.0)
- FastMCP
- MCP Protocol
- mVara
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。