How to Use the AudioStack MCP in Mastra AI

Q: How do I add AudioStack tools to a Mastra AI agent?

Initialize a new MCPClient with your Vinkius URL. Call listTools() on that client and spread the results directly into your agent's tool configuration array.

Q: Can Mastra AI pause an AudioStack workflow for human approval?

You can. Flag the createmix tool with requireToolApproval. The workflow will halt and wait for a producer to sign off before spending credits on the final master.

Automate complex audio production workflows using the AudioStack MCP Server and Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AudioStack MCP to Mastra AI

Create your Vinkius account to connect AudioStack 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 AudioStack with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient Pipelines with Mastra AI

Audio rendering takes time and occasionally drops requests. Mastra AI fixes this by wrapping the AudioStack tools in automated retry logic. If a `create_audioform` call times out, your workflow automatically backs off and tries again without writing custom error handlers. You can chain these operations together reliably. Set up a workflow that runs `text_to_speech`, waits for completion, and then conditionally triggers `create_mix` only if the client requested background music.

Dynamic Voice Selection

Hardcoding voice IDs breaks workflows when providers update their catalogs. Your agent can query `list_voices` to find the right match based on language or gender parameters at runtime. If a specific provider goes offline, the logic branches to find an alternative. Drilling down into specific actor traits happens through `get_voice_details`. The system pulls the exact pacing and tone data before committing to a long render. This prevents wasting credits on a voice that does not fit the project requirements.

Long-Form Story Automation

Generating a full audiobook requires careful state management. You trigger `create_story` and let Mastra handle the long-running execution. The framework's built-in memory tracks the progress across multiple chapters and scenes over the MCP connection. Once the heavy rendering finishes, you need to verify the output. The workflow calls `get_audioform` to grab the final URL, checks the file size, and pushes the finished asset to your cloud storage bucket.

Setup guide

Set up AudioStack 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 AudioStack 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: "audiostack-mcp-client",
  servers: {
    "audiostack-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent AudioStack 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 AudioStack. 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 AudioStack 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 AudioStack MCP in Mastra AI

Initialize a new MCPClient with your Vinkius URL. Call `listTools()` on that client and spread the results directly into your agent's tool configuration array.

You can. Flag the `create_mix` tool with `requireToolApproval`. The workflow will halt and wait for a producer to sign off before spending credits on the final master.

Yes, through built-in exponential backoff. If the API rejects a request, the workflow pauses and retries automatically.

Vinkius hosts the MCP Server for you. You connect your Mastra deployment to our endpoint, and we handle the uptime and scaling.

Your proprietary scripts and sound design templates flow through a zero-trust architecture. The Vinkius platform processes the data ephemerally, meaning nothing gets saved to disk after the session closes.

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