How to Use the Inworld AI MCP in Claude Code

Q: How do I add the Inworld AI MCP Server to Claude Code?

Run the command claude mcp add --transport http inworld-ai -- in your terminal. Ensure all configuration flags are placed before the server name.

Q: Does Claude Code support Inworld AI audio transcription?

Yes, it handles speech-to-text. Claude Code triggers the transcribeaudio tool to convert local WAV or MP3 files into plain text directly in your shell.

Q: Which tool should I use to list my custom voices?

Use listvoices to see all active vocal profiles in your workspace through this MCP toolset. The older listttsvoices tool is deprecated and should not be used for newer voice assets.

Run terminal commands to design voices, manage routers, and stream audio with the Claude Code CLI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inworld AI MCP to Claude Code

Create your Vinkius account to connect Inworld AI to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Inworld AI with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script voice generation from your terminal

The `design_voice` tool lets you generate new vocal profiles directly from a shell prompt. Claude Code sends your text description to the API and returns the voice identifier without needing a browser. To verify your assets, the CLI tool calls `list_voices` and prints the active profiles. You can then use `get_voice` to check the parameters or `delete_voice` to clean up old profiles during automated cleanup scripts.

Manage your MCP Server routers via command line

You can deploy new conversational routers by calling `create_router` directly from your terminal. This fits into your deployment pipelines, letting you spin up new character backends during CI/CD runs. The tool manages active configurations with `list_routers` and `update_router`. If a router is no longer needed, Claude Code runs `delete_router` to tear down the resource and save on workspace costs.

Pipe audio files through terminal tools

The `transcribe_audio` tool processes local audio files and prints the text output directly to stdout. This lets you pipe voice recordings into other CLI utilities or save them as text logs. For text-to-speech tasks, `synthesize_speech_sync` generates static audio files from text inputs. You can instantly test dialogue scripts by running a single command and playing the output file in your terminal audio player.

Setup guide

Set up Inworld AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see inworld-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Inworld AI transactions." It will automatically discover and invoke the available Inworld AI tools.

Terminal

claude mcp add --transport http inworld-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Inworld AI MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "inworld-ai-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Inworld AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Inworld AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Inworld AI MCP in Claude Code

Run the command `claude mcp add --transport http inworld-ai -- ` in your terminal. Ensure all configuration flags are placed before the server name.

Yes, you can run Claude Code headlessly in CI/CD environments. It can execute `create_router` or `clone_voice` as part of your automated game build and deployment pipelines.

Yes, it handles speech-to-text. Claude Code triggers the `transcribe_audio` tool to convert local WAV or MP3 files into plain text directly in your shell.

Use `list_voices` to see all active vocal profiles in your workspace through this MCP toolset. The older `list_tts_voices` tool is deprecated and should not be used for newer voice assets.

The server processes your voice files in ephemeral memory spaces that vanish immediately after execution. Your transcribed audio is never cached on Vinkius servers, keeping your sensitive voice recordings secure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript