How to Use the Deepgram MCP in Cursor

Q: Can I check Deepgram models directly in Cursor?

Ask the chat to run listavailablemodels for you. It returns the exact model names so you avoid typos in your configuration files.

Build voice features faster by giving Cursor direct access to Deepgram MCP Server transcripts and text-to-speech models.

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 Cursor

Create your Vinkius account to connect Deepgram to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test speech generation inside Cursor

Stop writing placeholder audio generation code. When you enable Agent mode, Cursor runs `convert_text_to_speech` to generate real audio files while you build the surrounding logic. The IDE pulls the exact bytes back into your workspace. You get to test your playback functions with actual API responses instead of relying on mock data.

Transcribe audio URLs via MCP Server

Feed a test audio link to your agent and watch it pull the transcript using `transcribe_audio_url`. The editor injects that real-world text straight into your test suites or database seed files. Knowing the exact JSON structure of the response helps you write better parsing logic. Your AI client sees the raw payload and writes the matching TypeScript interfaces automatically.

Audit your project usage mid-code

Hitting rate limits while testing is annoying. Ask the agent to fire `get_project_usage` to see your remaining balance without switching browser tabs. If you need to rotate credentials, `list_api_keys` and `list_deepgram_projects` give you the active environment details. You manage the infrastructure directly from your command palette.

Setup guide

Set up Deepgram MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Deepgram MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Deepgram transactions." If the MCP tools are loaded correctly, Cursor will call the Deepgram tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "deepgram-alternative-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 Cursor

Create a .cursor/mcp.json file in your project root. Add the Vinkius server URL under the mcpServers object and enable Agent mode.

Yes, and it uses real endpoints to do it. The agent calls the tools to understand the exact response shapes before writing your TypeScript definitions.

Ask the chat to run list_available_models for you. It returns the exact model names so you avoid typos in your configuration files.

Reloading the window ensures the agent picks up the new configuration. Just hit Command-Shift-P and select the reload option.

Your credentials never touch the client side. The ephemeral sandbox manages the connection to the provider, ensuring your project details and generated audio files remain strictly confidential.

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