mcpField
V
vrchat-mcp-osc

vrchat-mcp-osc

Local
github.com/KrekunGames & Entertainment31Updated 82w ago

About vrchat-mcp-osc

VRChat MCP OSC is an MCP server that connects AI assistants to VRChat through OSC, letting them control avatar parameters, movement and chatbox messages. It is aimed at users and developers who want AI-driven interaction in VR environments.

Key features

  1. 01Avatar parameter and expression control
  2. 02Movement and view direction control
  3. 03Chatbox message sending
  4. 04Menu and voice toggling
  5. 05Avatar name and parameter queries

Use cases

  1. 01Letting an AI assistant set avatar expressions in VRChat
  2. 02Sending chatbox messages from an AI assistant
  3. 03Querying the current avatar's name and parameters

MCP support

This project is an MCP server that exposes tools such as get_avatar_name, set_avatar_parameter, move_avatar and send_message to MCP clients, communicating with VRChat over OSC.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"vrchat-mcp-osc": {
"command": "npx",
"args": [
"-y",
"vrchat-mcp-osc"
]
}
}
}
Run commandnpx -y vrchat-mcp-osc

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmvrchat-mcp-osc

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

VRChat MCP OSC

VRChat MCP OSC provides a bridge between AI assistants and VRChat using the Model Context Protocol (MCP), enabling AI-driven avatar control and interactions in virtual reality environments.

Overview

By leveraging OSC (Open Sound Control) to communicate with VRChat, VRChat MCP OSC allows AI assistants such as Claude to:

  • Control avatar parameters and expressions
  • Send messages in VRChat
  • Respond to various VR events
    And more—all through the high-level API provided by the Model Context Protocol.

Key Features

  • Avatar Control: Manipulate avatar parameters and expressions
  • Movement Control: Direct avatar movement and orientation
  • Communication: Send messages through VRChat's chatbox
  • Menu Access: Toggle VRChat menu and interface elements
  • Avatar Information: Query avatar properties and parameters
  • Seamless VRChat Integration: Automatic detection of avatar configurations

System Requirements

  • Node.js 18 or higher
  • VRChat with OSC enabled
  • Claude Desktop (with MCP support)

Using with Claude Desktop

Clone and npm link
git clone https://github.com/Krekun/vrchat-mcp-osc
cd vrchat-mcp-osc
npm link
Configure Claude Desktop

Configure Claude Desktop by editing the claude_desktop_config.json file:

{
  "mcpServers": {
    "vrchat-mcp-osc": {
      "command": "npx",
      "args": [
        "vrchat-mcp-osc"
      ]
    }
  }
}
Command Line Options

The server supports various command-line arguments for customization:

# Claude Desktop configuration
{
  "mcpServers": {
    "vrchat-mcp-osc": {
      "command": "npx",
      "args": [
        "vrchat-mcp-osc",
        "--websocket-port", "8765",
        "--websocket-host", "localhost",
        "--osc-send-port", "9000",
        "--osc-send-ip", "127.0.0.1",
        "--osc-receive-port", "9001",
        "--osc-receive-ip", "127.0.0.1",
        "--debug"             
      ]
    }
  }
}
Available Options
OptionDescriptionDefaultNotes
--websocket-port <port>WebSocket port8765For WebSocket communication
--websocket-host <host>WebSocket hostlocalhostFor WebSocket communication
--osc-send-port <port>OSC send port9000Port for sending to VRChat
--osc-send-ip <ip>OSC send IP127.0.0.1Address for sending to VRChat
--osc-receive-port <port>OSC receive port9001Port for receiving from VRChat
--osc-receive-ip <ip>OSC receive IP127.0.0.1Address for receiving from VRChat
--debugEnable debug loggingfalseOutput detailed logs
--no-relayDisable relay serverfalseWhen not using relay server

Available MCP Tools

VRChat MCP OSC exposes the following MCP tools to AI assistants:

Tool NameDescription
get_avatar_nameRetrieves the current avatar's name
get_avatar_parametersLists available avatar parameters
set_avatar_parameterSets a specific avatar parameter
set_emote_parameterTriggers avatar emotes
move_avatarMoves the avatar in a specific direction
look_directionControls avatar's view direction
jumpMakes the avatar jump
menuToggles the VRChat menu
voiceToggles voice features
send_messageSends a message to the VRChat chatbox

Troubleshooting

Common Issues
  1. VRChat not responding to commands

    • Ensure OSC is enabled in VRChat settings
    • Check that the OSC ports match between VRChat and MCP configuration
    • Restart VRChat and Claude Desktop
  2. MCP server not starting

    • Ensure Node.js 18+ is installed
    • Check command line arguments for errors
    • Try running with --debug flag for more detailed logs
    • Use npx vrchat-mcp-osc -- --debug if direct arguments don't work
  3. NPX execution issues

    • If arguments aren't being recognized, try using the double dash format: npx vrchat-mcp-osc -- --debug
    • On Windows, try running in a command prompt with administrator privileges
    • If you're having trouble with global installation, try the local npm link approach

Project Structure

vrchat-mcp-osc/
├── packages/
│   ├── mcp-server/    # MCP server implementation (main entry point)
│   ├── relay-server/  # WebSocket to OSC relay
│   ├── types/         # Shared TypeScript interfaces
│   └── utils/         # Common utilities
└── pnpm-workspace.yaml  # Workspace configuration

Development

Build From Source
# Clone the repository
git clone https://github.com/Krekun/vrchat-mcp-osc
cd vrchat-mcp-osc

# Install dependencies
pnpm install

# Build all packages
pnpm -r build

# Development mode
pnpm -r dev

License

VRChat MCP OSC is dual-licensed as follows:

For Non-Commercial Use: You may use, modify, and redistribute the software under the terms of the MIT License. (See the MIT License file for details.)

For Commercial Use: Commercial use of this software requires a separate commercial license.

By using this software under the MIT License for non-commercial purposes, you agree to the terms of that license. Commercial users must obtain a commercial license as described above.

Acknowledgments

  • VRChat team for the OSC integration
  • Model Context Protocol for the standardized AI interface
  • Anthropic for Claude's MCP implementation

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.