How to Use the AssemblyAI MCP in Mastra AI

Q: How do I build a human-in-the-loop step for AssemblyAI in Mastra AI?

Set requireToolApproval on the deletetranscript tool within your client. Your Mastra AI workflow will pause and wait for an operator's manual confirmation before purging the AssemblyAI audio record.

Q: How do I fetch AssemblyAI sentence-level data for Mastra AI analysis?

Your Mastra AI agent can call gettranscriptsentences to receive a clean array of individual sentences. This makes it easy for Mastra AI to run sentiment analysis or keyword tagging on a granular level.

Build self-healing speech pipelines in Mastra AI using AssemblyAI to transcribe and analyze audio files.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to Mastra AI

Create your Vinkius account to connect AssemblyAI 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 AssemblyAI with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient speech-to-text workflows in Mastra AI

AssemblyAI audio processing fails for a dozen different reasons, from bad URLs to rate limits. Mastra AI lets you wrap `transcribe_audio` in a structured workflow that automatically retries when the API encounters transient errors. If the AssemblyAI transcription job still stalls, the Mastra AI workflow engine catches the failure and routes the task to a fallback handler. You write the logic once, and your Mastra AI agent handles the rest without crashing.

Automate AssemblyAI cleanup after Mastra AI workflows

Leaving raw AssemblyAI audio records sitting in your account is a security risk. This MCP Server lets you chain `delete_transcript` as the final step in your multi-step Mastra workflows. Once your Mastra AI agent finishes extracting insights from `get_transcript`, the system triggers the deletion. Your Mastra AI workflow verifies the `delete_transcript` call succeeded before marking the run as complete.

Branch Mastra AI workflows based on transcript structure

With this MCP Server, you can use `get_transcript_paragraphs` to check the density of the returned text before deciding which LLM to use for summarization. If `get_transcript_paragraphs` returns dozens of items, your Mastra AI agent routes the payload to a model with a larger context window. For short AssemblyAI snippets, Mastra AI uses a smaller, faster model to save on API costs.

Setup guide

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

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

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

You initialize the MCP connection with your Vinkius endpoint, call `listTools()`, and spread them directly into your agent's tool array. This gives your Mastra AI agent instant access to `transcribe_audio` and other AssemblyAI features.

Yes, you can configure Mastra's workflow engine to automatically retry failed `get_transcript` calls with exponential backoff. This ensures your AssemblyAI transcription pipeline remains stable even under heavy load.

Set `requireToolApproval` on the `delete_transcript` tool within your client. Your Mastra AI workflow will pause and wait for an operator's manual confirmation before purging the AssemblyAI audio record.

Your Mastra AI agent can call `get_transcript_sentences` to receive a clean array of individual sentences. This makes it easy for Mastra AI to run sentiment analysis or keyword tagging on a granular level.

Your AssemblyAI media files and text outputs are processed entirely in memory inside an isolated, zero-trust container. The connection to the AssemblyAI API is direct and encrypted, ensuring your Mastra AI pipeline's speech data is never cached or leaked.

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