Agent Vrm Mcp

Agent Vrm Mcp is an MCP server that provides text-to-speech generation and 3D avatar visualization by interfacing with the AgentVRM engine. Built with Python and available via uvx, it connects MCP-compatible clients such as Claude Desktop to an active AgentVRM instance, allowing the assistant to speak out loud while driving avatar lip-sync, facial expressions, and animations. The server exposes the speak_text tool, which accepts user input text alongside optional parameters for speaker identity, speech speed scaling, and automatic playback toggling. Generated audio is automatically played using operating system utilities like default Windows players, afplay on macOS, or aplay on Linux, and files are saved as WAV files in an assets directory. Software developers, digital avatar creators, and interactive AI designers use this server to turn standard LLM text completions into vocalized, animated Japanese avatar presentations directly from their desktop AI workflows.

Category: Other & General Purpose

Tags: demo, example, template

Visit Agent Vrm Mcp

How to install and configure Agent Vrm Mcp

1. Ensure Python 3.10 or higher is installed and start an AgentVRM engine instance running locally or remotely (default URL: http://localhost:3001/api/speak_text). 2. Open your Claude Desktop configuration file (claude_desktop_config.json). 3. Add the server entry under the mcpServers object: json { "mcpServers": { "vrm": { "command": "uvx", "args": ["agent-vrm-mcp", "--api-url=http://localhost:3001/api/speak_text"] } } } 4. Restart Claude Desktop to activate the connection to AgentVRM.

What you can do with Agent Vrm Mcp

• Vocalizing Claude Desktop chat responses using an animated 3D VRM avatar with matching mouth and face animations. - Converting text to speech files stored automatically in the local assets directory as standard WAV audio. - Adjusting voice output speeds and speaker IDs to customize the avatar delivery during conversational sessions. - Playing synthesized audio hands-free through native operating system media tools across Windows, macOS, or Linux. - Testing agent-driven speech generation locally using the MCP Inspector tool against active AgentVRM endpoints.

Key facts

• https://github.com/Sunwood-ai-labs/agent-vrm-mcp
• Other & General Purpose
• demo, example, template

Part of MCP Servers

What is Agent Vrm Mcp?

Agent Vrm Mcp is a Model Context Protocol server that bridges MCP clients like Claude Desktop with an AgentVRM engine. It allows AI models to speak text aloud using 3D VRM avatars with expressions and animations.

What tools does Agent Vrm Mcp provide?

It provides the speak_text tool. This tool requires a text string and accepts optional parameters including speaker_id, speed_scale, and an auto_play boolean to control automatic platform audio playback.

What prerequisites are needed to use this server?

You need Python 3.10 or higher and an active AgentVRM engine running either locally or on a remote network. By default, it targets http://localhost:3001/api/speak_text unless overridden with the --api-url argument.

How does audio playback work across different platforms?

The server automatically plays generated audio files using native system tools. It uses the default system player on Windows, afplay on macOS, and attempts aplay with an xdg-open fallback on Linux.

Is Agent Vrm Mcp open source?

Yes, Agent Vrm Mcp is open source software released under the MIT license, allowing for free use, modification, and distribution according to license terms.