How to Use the Deepgram MCP in Mastra AI

Q: Can a Mastra AI agent manage multiple Deepgram projects?

Yes, the agent can call listprojects to discover active environments and dynamically switch contexts. This allows your Mastra AI workflows to route audio processing tasks to different billing profiles based on the user's account data.

Build resilient, multi-step audio processing workflows with Mastra AI and the Deepgram MCP Server.

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

Build automated audio pipelines with Mastra AI

If a customer uploads an audio file, your Mastra AI workflow can automatically route it to Deepgram's `transcribe_url` tool. The Mastra AI conditional logic checks the Deepgram transcript output, and if it detects churn signals, it triggers an immediate escalation. This integration lets you build complex branching paths in Mastra AI without hardcoding Deepgram API endpoints. The Deepgram MCP Server exposes tools directly to your Mastra AI agent, allowing it to choose between transcription or voice synthesis.

Automate Deepgram key rotation in Mastra AI

Use Mastra AI workflows to automatically cycle Deepgram keys when usage limits are breached. By combining Deepgram's `get_usage` with `create_key` and `delete_key`, your Mastra AI agent can monitor account health. If a Deepgram API call fails due to rate limits, Mastra AI handles the exponential backoff automatically. The Mastra AI agent retries the Deepgram tool execution without crashing your main application thread.

Trigger Deepgram voice synthesis via Mastra AI workflows

Generate Deepgram voice responses programmatically when a Mastra AI workflow step completes. The Deepgram `speak_text` tool allows your Mastra AI agent to convert written summaries into audio files. Because Mastra AI manages state across steps, you can pass the Deepgram transcript directly into the voice generator. The Deepgram MCP Server ensures the voice output matches your exact Mastra AI configurations.

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-mcp-client",
  servers: {
    "deepgram-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

You define a retry policy in your Mastra AI workflow configuration for the specific Deepgram tool. If `transcribe_url` hits a rate limit, the framework automatically backs off and retries the request.

Yes, the agent can call `list_projects` to discover active environments and dynamically switch contexts. This allows your Mastra AI workflows to route audio processing tasks to different billing profiles based on the user's account data.

You store your Deepgram credentials in the Vinkius vault, which injects them directly into the MCP Server environment. Your Mastra AI code only connects to the Vinkius endpoint, keeping your master tokens out of your workflow codebases.

Yes, you can set the requireToolApproval flag on sensitive tools like delete_key or send_invite. This pauses the workflow until an admin approves the action, preventing accidental credential deletion.

Your audio URLs and transcription payloads pass through secure, ephemeral memory during the Mastra AI workflow execution. Vinkius isolates the Deepgram MCP Server processes, ensuring no transcript text or audio data is written to persistent disk storage.

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