Gesture Harness
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Gesture Harness
Give your LLM some body language. Gesture Harness is a small MCP server that lets Claude, Codex, Cursor or any other MCP client play the gestures of an animated 3D character: a wave hello, a nod, a thumbs-up, a dance when something works. The character appears in a browser page you keep open, on your screen or on a spare phone or tablet beside it.
It comes with a robot to try. To use your own character, point it at any .glb file that has animations: every animation clip in the file becomes a gesture the LLM can ask for, and any facial morph targets become expressions. Nothing needs to be configured for a new model.

What you need
Node.js 18 or newer. There is nothing to install beyond the repository.
An MCP client, such as Claude Desktop, Claude Code, Codex or Cursor.
A browser to show the character. The page loads three.js from a CDN, so the browser needs to be online.
Optionally, your own character: a binary glTF (
.glb) with named animation clips. Without one you get the bundled robot.
The character is an animation on screen. Nothing physical moves.
Related MCP server: Persona Motion Studio
Try it
git clone https://github.com/DanP20/gesture-harness.gitAdd it to your MCP client, using the full path to src/server.js:
Claude Code
claude mcp add gestures -- node /full/path/to/gesture-harness/src/server.jsClaude Desktop (Settings, Developer, Edit Config) or Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"gestures": { "command": "node", "args": ["/full/path/to/gesture-harness/src/server.js"] }
}
}Codex (~/.codex/config.toml)
[mcp_servers.gestures]
command = "node"
args = ["/full/path/to/gesture-harness/src/server.js"]Restart the client, open http://localhost:7444 in a browser, and ask: "Make the robot wave."
To see a model's gestures without an LLM, run node src/server.js --serve and open http://localhost:7444/?buttons. It shows a button for each gesture and expression.
What the LLM gets
Tool | What it does |
| The gestures and how long each one lasts, the expressions, and whether anyone has the viewer open |
| Plays one gesture, |
| Sets a facial expression for a few seconds ( |
The tool descriptions name the gestures and suggest using them sparingly, when they fit what is being said. If nobody has the viewer open, a call fails with a message telling the LLM where the viewer is.
Bring your own character
node src/server.js --model ~/models/fox.glb --name "the fox"The model needs to be a .glb with its animation clips named the way you want the LLM to see them, such as Wave or Dance. Some places to find or make one:
Quaternius: free (CC0) animated characters. The bundled robot is one of them.
Mixamo: pick a character and some animations, then combine them into a single
.glbin Blender, with one action per gesture.Your own rig, exported from Blender as glTF Binary with animations included.
The clip with "idle" in its name loops between gestures. Use --idle to pick a different one, and --gestures Wave,Nod,Dance to offer only some of the clips. Morph targets (shape keys) named in the file, like Smile or Angry, become expressions.
Options
Flag | Environment variable | Default | |
|
| the bundled robot | the |
|
| "the robot" | what the LLM is told the character is called |
|
| the first clip with "idle" in its name | the clip that loops between gestures |
|
| every clip except the idle one | a comma-separated list of clips to offer |
|
| 7444 | where the viewer is served |
|
| 127.0.0.1 |
|
| keep running without an MCP client |
For the bundled robot, the default list leaves out its Death, Sitting and Standing clips.
The viewer page has its own options in the address:
?bg=transparent: no background, for OBS and other streaming tools.?bg=ffffff: any background colour, as a hex code.?clean: hides the line of text.?buttons: shows the try-it buttons.
How it works
MCP client ──stdio──▶ gesture-harness ──server-sent events──▶ viewer page (three.js)
reads the clips and expressions plays the clip, then
straight from the .glb fades back to idleThe MCP client starts the harness. The harness reads the clip names, their lengths and the morph targets from the .glb, and serves the viewer and the model on localhost. When a gesture is called, it tells every open viewer to play it, then waits for the clip's length before it answers.
You might have two MCP clients open at once, say Claude Desktop and Codex. The first copy holds the port, and the second passes its requests to the first, so both clients drive the same character.
It uses no npm packages: one Node file for the server, and one page for the viewer.
Where it came from
This began as gestures for a robot on a little round desk screen that sat beside an AI voice chat. Asked to wave or celebrate, the robot did it. Gesture Harness is the general version: any character, any MCP client, any screen with a browser.
Credits
The bundled robot is RobotExpressive, modelled by Tomás Laulhé (Quaternius) and released CC0 1.0. Don McCurdy added the facial expressions and converted it for three.js. The viewer uses three.js (MIT).
Licence
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate, edit, and deploy immersive 3D/WebGL web projects from any MCP assistant.
Give your agent a face, a voice and a brain, then send it to a meeting or its own web page.
Skills, agents and memory in the cloud, plus a gateway to your other MCP servers.
Give your AI a face, a voice, and a personality. 3D avatars with custom personas.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI systems to control the Reachy Mini robot—speak, listen, see, and express emotions through physical movement. Compatible with Claude, GPT, Grok, and other MCP-compatible AIs.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to show, animate, and control a VRM character on the desktop, including posing and motion installation via MCP tools.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to control a desktop virtual character (VRM) by playing animations, showing/hiding the character, and checking runtime status through the MCP protocol.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to drive a transparent, always-on-top Live2D desktop mascot over Streamable HTTP: playing motion sequences, changing expressions, showing speech bubbles, repositioning the window or the character within it, and hot-switching models, with query tools for available motions, expressions, models, and current status.1MIT