How to Use the Vibrato MCP in Mastra AI

Q: How does Vibrato work with complex workflows in Mastra AI?

You integrate it by calling mcpClient.listTools() and feeding those tools into your agent framework's tool list. This lets the workflow engine decide when to initiate a phone call.

Q: Can I use Vibrato to check call status in Mastra AI?

Yes, getcallstatus is perfect for this. Your built-in workflow engine can pause and wait for the result of this tool before moving to the next step.

Q: What if I need to list available call templates in Mastra AI?

You just run listtemplates. The resulting data feeds right into your workflow engine, allowing you to build logic that routes based on available scripts.

Build Resilient Phone Workflows: Complex Call Automation with 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 Vibrato MCP to Mastra AI

Create your Vinkius account to connect Vibrato 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 Vibrato with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Calls from Templates

Mastra AI uses `create_call_from_template` to launch calls based on established processes, like negotiating a bill. This means you don't worry about prompt engineering; the template does that heavy lifting for you. This fits right into your multi-step workflow engine, handling initial setup before any complex logic kicks in.

Monitor and List All Conversations

You can build failure handling around `list_calls` or use `get_call_status` to check the state of a conversation. If one call fails, your workflow can immediately pivot to inspect the status before retrying. This visibility is key for creating robust systems that need to handle unexpected outcomes gracefully.

Initiate Calls Programmatically

The `create_call` tool lets you start a call from scratch, passing specific data points like the prompt and phone number. This is your entry point for new types of automated interactions. Your agent framework can use this as the first step in a conditional branch—if condition X is met, then call this function.

Setup guide

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

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

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

You integrate it by calling `mcpClient.listTools()` and feeding those tools into your agent framework's tool list. This lets the workflow engine decide when to initiate a phone call.

Yes, `get_call_status` is perfect for this. Your built-in workflow engine can pause and wait for the result of this tool before moving to the next step.

You just run `list_templates`. The resulting data feeds right into your workflow engine, allowing you to build logic that routes based on available scripts.

It's built for it. Your agent framework handles the sequence: check status, then initiate a call, and finally process the outcome through conditional branching.

The server manages phone numbers used in calls and the associated status metadata. Your workflow can use this information to decide if a retry is necessary or if the process should end.

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