How to Use the Deepgram MCP in VS Code Copilot

Q: How does the shared config for Deepgram and VS Code Copilot work?

You create a .vscode/mcp.json file in your project's root directory and add the Deepgram MCP Server details. Once you commit and push that file, every team member who pulls the repo will have those tools available to Copilot automatically.

Equip your entire team with Deepgram tools inside VS Code. Share one config and let Copilot handle audio AI tasks for everyone.

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 VS Code Copilot

Create your Vinkius account to connect Deepgram to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

A Shared Deepgram Toolbox for Your Team

The power here is the shared configuration. Add this MCP Server to your project's `.vscode/mcp.json` file and commit it. Now every developer on your team automatically gets the same set of Deepgram tools inside their editor. No more 'it works on my machine'. When a dev asks Copilot to `transcribe_url`, it uses the same sanctioned tool as everyone else. This ensures consistency across your entire engineering organization.

Let Copilot Handle Deepgram Account Admin

Your team can now ask Copilot to manage Deepgram resources directly. Need a new key for a staging environment? Ask Copilot to `create_key`. Want to check if a teammate has access? Use `list_members`. This offloads routine tasks from your platform team. Developers can self-serve API keys and check `get_usage` without filing a ticket. It's secure, logged, and controlled through the MCP Server.

Build and Test Audio Features in VS Code

When you're building an application that needs audio, you can use Copilot to interact with Deepgram in real time. Ask it to `speak_text` with some sample copy to hear how it sounds, or feed it a URL to `transcribe_url` to test your parsing logic on a real transcript. This makes development much faster. You're not working with mock data; you're using the actual Deepgram service from your editor. Your agent becomes a true partner in building and testing audio-driven features.

Setup guide

Set up Deepgram MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Deepgram MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Deepgram tools listed. Try asking: "List my recent Deepgram transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "deepgram-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VS Code Copilot

You create a `.vscode/mcp.json` file in your project's root directory and add the Deepgram MCP Server details. Once you commit and push that file, every team member who pulls the repo will have those tools available to Copilot automatically.

Yes, the MCP model allows for this. Your Vinkius admin can configure which tools, like `create_key` or `delete_key`, are exposed to your team's VS Code Copilot, giving you granular control.

It is. The server runs in a Vinkius zero-trust sandbox, and all communication is encrypted. Since you can manage the configuration via your repository, it fits perfectly into existing enterprise SOC 2 and IT governance workflows.

Your team can ask Copilot to transcribe audio from links, generate speech from text, manage API keys, check account balances, and invite new members to a project. It handles all the interaction with the Deepgram API.

The server only processes data required by the specific tool you invoke, like a URL for transcription or text for speech generation. Vinkius infrastructure is ephemeral, so your API credentials and audio-related data are never persisted or logged.

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