How to Use the Inworld AI MCP in Mastra AI

Q: Does Inworld AI allow human-in-the-loop with Mastra AI?

Absolutely. You can use the requireToolApproval setting in Mastra to pause the workflow before the agent executes a specific voice or router task.

Build complex, voice-enabled agent workflows in Mastra AI with automatic retries.

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 Mastra AI

Create your Vinkius account to connect Inworld AI to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated voice workflows in Mastra AI

Build multi-step agent paths that include speech synthesis as a standard node. Using `synthesize_speech_sync`, your Mastra workflows can generate audio responses as part of a larger chain of events. If a call fails, Mastra handles the retry logic automatically. You don't have to write custom wrappers for transient network issues.

Conditional agent logic with routers

Control how your agents behave across different branches of a Mastra workflow. You use `list_routers` to check current character configurations and `create_router` to define new logic paths for your agents. This allows your agents to pivot their tone or intent based on the outcome of previous steps in the workflow. It keeps your agent logic modular.

Voice management for long-running agents

Keep your agent's identity consistent by managing voices through `list_voices` and `get_voice`. You can verify which voice profile is active before an agent executes a speech task. This is vital for long-running agents that need to maintain a specific persona over hours of interaction. You can also delete outdated profiles using `delete_voice` to keep your workspace clean.

Setup guide

Set up Inworld AI MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Inworld AI tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "inworld-ai-mcp-client",
  servers: {
    "inworld-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Inworld AI Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Inworld AI tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Inworld AI transactions"
);
console.log(result.text);

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 Mastra AI

You initialize an MCP client within your Mastra agent definition. Once connected, you spread the available tools into your agent's tool array.

Yes. Mastra supports built-in retries for MCP tool calls. If a speech synthesis request hits a hiccup, the framework handles the recovery.

Absolutely. You can use the `requireToolApproval` setting in Mastra to pause the workflow before the agent executes a specific voice or router task.

Since Mastra supports one-command deployment, you just ensure your environment variables for the MCP server are set. The agent will connect to the endpoint on startup.

All character definitions and voice samples are restricted to your workspace. The connection is authenticated via your endpoint token, ensuring no unauthorized access to your voice assets.

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