How to Use the Deepgram MCP in Mastra AI

Q: What's the setup for the Deepgram MCP Server with Mastra AI?

You add the Vinkius URL to your MCPClient configuration in your Mastra AI project. Mastra's client will then automatically discover and register all the available Deepgram tools for your agents to use.

Q: Can my Mastra AI agent manage my Deepgram API keys?

It can list them. The listapikeys tool allows an agent to get a list of active keys for a specific project, which is useful for auditing or monitoring tasks within your automated workflows.

Build failure-proof audio workflows. Transcribe, generate speech, and manage keys with Deepgram tools inside your Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to Mastra AI

Create your Vinkius account to connect Deepgram 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 Deepgram with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Conditional Audio Workflows

This server's tools plug directly into Mastra AI's workflow engine. Your agent can use `transcribe_audio_url` to get text from an audio file, and then use Mastra's logic to decide the next step. If the transcript contains 'urgent', it can trigger another action. If not, it can archive the file. This isn't just a simple API call. You're building stateful, multi-step jobs. For example: transcribe a customer service call, check the text for negative sentiment, and if found, automatically create a ticket in your helpdesk. Mastra handles the branching logic for you.

Reliable Deepgram Account Automation

Use the `get_project_usage` tool to have an agent monitor your Deepgram API credits. Mastra's real power here is its built-in resilience. If the API call to check your usage fails for some reason, Mastra automatically retries with exponential backoff. You don't need to write any error-handling code for that. Your agent will either get the data or fail gracefully after multiple attempts, letting you build monitoring that you can actually trust. This MCP Server makes your backend agents more robust.

Chain Tools for Complex Tasks

Mastra AI excels at chaining operations. An agent can process a batch of data, generate a summary, and then immediately call the `convert_text_to_speech` tool to turn that summary into an audio report. Because Mastra manages the state between steps, you can build sophisticated pipelines. The output of one Deepgram tool becomes the input for the next part of your workflow, whether that's another tool call or some custom code.

Setup guide

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

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

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

Mastra has automatic retries with exponential backoff built-in. If a call to a Deepgram tool like `transcribe_audio_url` fails due to a network issue, Mastra will try again without you writing any extra code.

Yes, that's exactly what it's for. Your Mastra AI agent can use the `transcribe_audio_url` tool, then use conditional logic within your workflow to analyze the resulting text and trigger different actions.

You add the Vinkius URL to your `MCPClient` configuration in your Mastra AI project. Mastra's client will then automatically discover and register all the available Deepgram tools for your agents to use.

It can list them. The `list_api_keys` tool allows an agent to get a list of active keys for a specific project, which is useful for auditing or monitoring tasks within your automated workflows.

Your agent sends audio URLs and text for speech synthesis. Vinkius processes these requests in isolated, single-use sandboxes. The connection is stateless, and the payload data sent to Deepgram is never logged or stored on our platform.

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