How to Use the Inworld AI MCP in Windsurf

Q: How do I connect the Inworld AI MCP Server to Windsurf?

Add the server configuration to your /.codeium/windsurf/mcpconfig.json file. You can also use the Settings menu under Cascade, navigate to MCP Servers, and paste the connection details.

Q: Does the Inworld AI integration with Windsurf support speech streaming?

Yes, it supports real-time audio generation. Cascade calls synthesizespeechstream to fetch chunked audio data, which you can pipe directly into your application's audio buffer.

Q: How do I manage LLM models for my dialogue routers?

Run listmodels to see what LLM options are available in your workspace. You then pass the selected model name to your router configuration tools.

Q: How does this server handle the privacy of my voice samples?

All audio files sent to clonevoice are processed in secure, ephemeral V8 isolates. Your raw audio recordings never persist on the host system, and connections to the voice API use TLS encryption to protect your proprietary vocal data.

Give Cascade the power to design voices, clone audio, and route complex dialogue directly inside your Windsurf IDE with this MCP Server.

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 Windsurf

Create your Vinkius account to connect Inworld AI to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build custom voice profiles directly in Windsurf

You can instruct Cascade to generate custom voices from a simple text prompt using the `design_voice` tool. If you have existing audio files, the agent runs `clone_voice` to match the exact vocal profile you need. This lets you build out entire game casts or assistant voices without leaving your workspace. To keep things organized, the agent manages the entire lifecycle of these assets. It checks current profiles with `list_voices`, pulls specific details via `get_voice`, and updates them using `update_voice`. You get immediate feedback on voice assets while writing your game or application code.

Configure smart dialogue routers inside Windsurf

Setting up conversational flows starts with `create_router` to establish your LLM-driven dialogue paths. Cascade analyzes your project structure, determines how characters should interact, and configures the router behavior to fit your narrative architecture. When your game logic changes, the agent modifies these paths using `update_router` or removes old configurations with `delete_router`. It verifies active paths by calling `list_routers` and `get_router` to ensure your characters always use the correct LLM backend.

Test voice outputs with the Windsurf MCP Server

The `synthesize_speech_sync` tool converts your text strings into playable audio files instantly. Cascade triggers this tool during development to let you hear how dialogue sounds before committing code. For real-time applications, the agent sets up streaming audio pipelines using `synthesize_speech_stream`. It also processes incoming voice recordings with `transcribe_audio` to build responsive, two-way vocal interfaces.

Setup guide

Set up Inworld AI MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Inworld AI payment history." If connected, Cascade will call the Inworld AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "inworld-ai-mcp": {
      "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 Windsurf

Add the server configuration to your `~/.codeium/windsurf/mcp_config.json` file. You can also use the Settings menu under Cascade, navigate to MCP Servers, and paste the connection details.

Yes, Cascade handles the entire sequence without manual intervention. You tell it to clone a voice, and it finds the audio file, calls `clone_voice`, and then uses `publish_voice` to make it live.

Yes, it supports real-time audio generation. Cascade calls `synthesize_speech_stream` to fetch chunked audio data, which you can pipe directly into your application's audio buffer.

Run `list_models` to see what LLM options are available in your workspace. You then pass the selected model name to your router configuration tools.

All audio files sent to `clone_voice` are processed in secure, ephemeral V8 isolates. Your raw audio recordings never persist on the host system, and connections to the voice API use TLS encryption to protect your proprietary vocal data.

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