Reachy Mini MCP Server

Most AI and media services work still happens through a UI a human drives. Reachy Mini MCP MCP server moves it into the conversation instead. Control the Reachy Mini robot (or simulator) from Claude, ChatGPT, or any MCP-compatible client.

The tools it exposes

The server publishes 14 tools. What each one is for:

• capture_image — Capture a JPEG frame from the robot's HD camera
• scan_surroundings — Pan camera across multiple angles and return a panoramic set of images
• track_face — Detect a face via OpenCV and turn head to face it
• move_head — 6-DOF head positioning (x/y/z in mm, roll/pitch/yaw in degrees)
• move_antennas — Independent antenna control (-3.14 to 3.14 radians)
• look_at_point — Orient head toward a 3D point in world coordinates
• express_emotion — Emoji-driven emotion system with synchronized movements and sounds
• play_sound — Play built-in sounds (wake_up, go_sleep, confused1, impatient1, dance1, count)
• speak_text — Text-to-speech via ElevenLabs API, played through robot speaker
• detect_sound_direction — Microphone array direction-of-arrival + speech detection
• wake_up — Built-in greeting animation with sound
• go_to_sleep — Built-in farewell animation with sound

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What it needs from you

Configuration is passed through the environment: ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, REACHY_ELEVENLABS_API_KEY, REACHY_ELEVENLABS_VOICE_ID, ELEVENLABS_MODEL_ID, REACHY_ELEVENLABS_MODEL_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

• Python 3.13+ - Reachy Mini robot or the Reachy Mini simulator - uv (recommended) or pip

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Reachy Mini MCP's toolset — capture_image, scan_surroundings, track_face and 11 more — is a fair guide to whether it matches your workflow. It is maintained by arturskowronski; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Reachy Mini MCP.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.