An astronaut overseeing a futuristic data hub

Connect Inworld AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your agents lifelike voices and intelligent personality routing.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 19 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 19 available through Inworld AI.

  1. 01

    List voices

    Get a list of all voices currently in your workspace.

  2. 02

    Chat completions

    Generate chat responses by routing the request through an LLM Router.

  3. 03

    Clone voice

    This capability creates a new voice by analyzing provided audio samples.

  4. 04

    Create realtime call

    Initiate a WebRTC realtime call for low-latency voice interaction.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 19 available through Inworld AI.

  1. 05

    Create router

    Set up a new LLM Router to manage character orchestration.

  2. 06

    Design voice

    Create a unique voice persona by providing a text description.

  3. 07

    List models

    This capability provides a list of all available LLM models in your account.

  4. 08

    List tts voices

    This deprecated capability lists TTS voices from the older Voice API.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 19 available through Inworld AI.

  1. 09

    Publish voice

    Use this to move a draft or preview voice into your published library.

  2. 10

    Synthesize speech stream

    This capability generates speech through a continuous stream for real-time interaction.

  3. 11

    Synthesize speech sync

    Generate a single speech audio file synchronously.

  4. 12

    Transcribe audio

    Convert audio files into text for your agent to process.

Capability set04 / 05

13-16

4 capabilities in this set.

Part of 19 available through Inworld AI.

  1. 13

    Delete router

    This capability removes an existing LLM Router from your workspace.

  2. 14

    Delete voice

    Use this to permanently delete a specific voice asset.

  3. 15

    Get router

    This capability retrieves the configuration details for a specific LLM Router.

  4. 16

    Get voice

    Get the specific metadata and settings for a single voice.

Capability set05 / 05

17-19

3 capabilities in this set.

Part of 19 available through Inworld AI.

  1. 17

    List routers

    Retrieve a full list of your configured LLM Routers.

  2. 18

    Update router

    Modify the settings or configuration of an existing LLM Router.

  3. 19

    Update voice

    Change the properties or settings of a specific voice.

Real work

What teams actually run

01

Dynamic NPCs

Game developers can create non-player characters that speak with unique, consistent voices.

02

Automated Voiceovers

Content creators can turn written scripts into spoken dialogue using cloned or designed voices.

03

Interactive Agents

Engineers can build agents that listen via transcription and respond via streaming speech.

04

Persona Management

Users can organize and update entire libraries of vocal assets and character routers.

Automate a task

Put Inworld AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Inworld AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Inworld AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1030ms average. Fast in production.

Inworld AI is checked daily against the live service.

Daily averagePeak 1241ms
Oct 3Today
Fastest day
772ms
Slowest day
1241ms
14-day trend
Improving-15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 19 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Inworld AI, so you can see the experience inside your AI.

It does not authenticate your account with Inworld AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Inworld AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_3lkEwqqakpRf4XlQXHb3G8jJBe7cyrieiM1PCdg3/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Inworld AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "inworld-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_3lkEwqqakpRf4XlQXHb3G8jJBe7cyrieiM1PCdg3/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Inworld AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Inworld AI owners hand off.

This MCP is built for developers and creators who need to move beyond text-only AI. It bridges the gap between logic and personality.

  • 01

    Game Developers

    They hand off character personality and voice generation to the agent.

  • 02

    Content Creators

    They use the agent to automate voiceovers and character dialogue.

  • 03

    AI Engineers

    They build agentic workflows that require multimodal interaction and routing.

FAQ

Questions Inworld AI owners ask.

  • 01

    How do I create a new voice?

    You can use design_voice to create a voice from a text description, or use clone_voice to replicate a voice from an audio sample.

  • 02

    Can I use this for real-time conversations?

    Yes, you can use synthesize_speech_stream for streaming audio or create_realtime_call to initiate WebRTC calls.

  • 03

    What clients can I use with this MCP?

    You can connect this MCP to any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Do I need my own API keys?

    Yes, you will need to provide your Inworld API Key and API Secret from your Inworld Studio account.

  • 05

    How does character routing work?

    You can use create_router to set up an LLM Router, which then manages how chat completions are handled for your characters.

  • 06

    How can I create a custom voice using only a text description?

    You can use the design_voice capability. Simply provide a prompt like 'Warm, friendly male voice' and a preview text. The capability will generate voice options that you can later publish to your library.

  • 07

    What is the difference between synchronous and streaming speech synthesis?

    Use synthesize_speech_sync to receive the full audio file once processing is complete. Use synthesize_speech_stream for real-time applications where you want to receive audio chunks as they are generated for lower latency.

  • 08

    Can I manage multiple AI characters or models through this server?

    Yes. You can use list_routers and get_router to manage your orchestration layers, and list_models to see available AI models in your Inworld workspace.

Connect Inworld AI to Claude, Cursor, ChatGPT & more