How to Use the Verbit MCP in Mastra AI

Build complex, reliable transcription workflows with Verbit using 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 Verbit MCP to Mastra AI

Create your Vinkius account to connect Verbit 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 Verbit with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verbit MCP Server Workflow Engine

Start by calling `create_job` to upload your media file. Because you’re using Mastra AI, the entire workflow is built into a repeatable process. The agent sends the job and then waits for confirmation or status updates. The framework manages this state automatically. You don't just call tools; you build reliable steps that handle the asynchronous nature of transcription jobs.

Checking Verbit Job Status

The `get_job` tool lets your agent check job progress using its ID. If a job fails or times out, Mastra AI's built-in retries kick in, automatically attempting to poll the status again with exponential backoff. This means if the initial connection to Verbit is flaky, you don't lose the workflow; the agent tries again until it gets a solid read on the job's status.

Retrieving Transcripts from Mastra AI

After confirming success with `get_job`, you use `get_transcript` to download the final caption data. If this download fails, the workflow doesn't crash; it uses its built-in failure handling mechanisms. This guarantees that even if network issues pop up when fetching the results, your complex multi-step process will try until it gets the required file.

Setup guide

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

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

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

Mastra AI's workflow engine automatically handles failures. If `get_job` times out, the platform retries the call using exponential backoff, ensuring your process doesn’t stop because of a temporary network dip.

Verbit is designed to accept various types of media files for transcription. You send the file using `create_job`, and the system manages the processing on its end.

Yes, you can set up required tool approvals. For instance, after `get_job` confirms completion, the workflow might pause and require human review before calling `get_transcript`.

This server deals with media files during job creation and outputs structured caption transcripts when you call `get_transcript`. The workflow manages the transition between these two types of data.

Use Mastra AI. Its built-in features, like automatic retries and conditional branching, make sure that if any single tool call fails—whether it's `get_job` or `create_job`—the overall workflow doesn't break.

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