How to Use the Vapi MCP in Mastra AI

Q: How do I ensure reliable call logging with Vapi and Mastra AI?

Use the getcalldetails tool. It retrieves not just the transcript, but also specific metrics for the call session. This data is crucial for auditing complex workflows.

Q: Can I automate call setup using Vapi and Mastra AI?

Yes. The framework integrates createphonecall into its workflow engine. You can build a flow that automatically attempts to connect, handles failures, and reports back.

Q: Does Mastra AI support multi-agent collaboration with the MCP Server?

Yes, it supports defining 'squads' using listsquads. You can set up multiple specialized agents to work together on a single complex task.

Q: How do I check which tools are available for my Mastra AI workflow?

Call listagenttools. This gives you a definitive list of every operation Vapi assistants can run, letting you build accurate conditional logic in your flow.

Build resilient workflows with Vapi and Mastra AI's agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to Mastra AI

Create your Vinkius account to connect Vapi 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 Vapi with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex multi-step processes via MCP Server

Mastra AI uses the server to execute sophisticated, conditional logic. For example, if a payment fails, the workflow can use Vapi tools to trigger an automatic retry with different credentials before notifying your admin. This handles failures gracefully and ensures complex business rules are always followed through automated retries.

Manage assistant lifecycles using Mastra AI

The framework allows you to define and manage assistants. Use `create_assistant` to set up the initial persona, or use `update_assistant` if requirements change mid-workflow. You maintain full control over the agent's configuration. It also lets you list all existing personas via `list_assistants`, keeping track of everything.

Control outbound calling sequences with Mastra AI

When a workflow needs human contact, it initiates an outbound call. You use `create_phone_call` by providing the necessary number and customer details directly into the agent's step-by-step process. The system tracks these calls through tools like `list_calls`, allowing the workflow to monitor progress.

Setup guide

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

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

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

Use the `get_call_details` tool. It retrieves not just the transcript, but also specific metrics for the call session. This data is crucial for auditing complex workflows.

Yes. The framework integrates `create_phone_call` into its workflow engine. You can build a flow that automatically attempts to connect, handles failures, and reports back.

This server manages call metadata, including transcripts, phone number IDs, and customer contact details passed during outbound calls. This is critical PII.

Yes, it supports defining 'squads' using `list_squads`. You can set up multiple specialized agents to work together on a single complex task.

Call `list_agent_tools`. This gives you a definitive list of every operation Vapi assistants can run, letting you build accurate conditional logic in your flow.

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