How to Use the Deepgram MCP in Cursor

Q: Can I manage my whole Deepgram account from inside Cursor?

Yes, the MCP server gives you tools for key management (createkey), project listing (listprojects), and usage tracking (getusage). You can run all your Deepgram admin tasks without leaving your editor.

Q: What's the setup process for Deepgram in Cursor?

It's simple. You add the MCP Server configuration to a mcp.json file in your project or home directory. Once that's saved, the Deepgram tools are available to the agent in chat.

Let Cursor write your Deepgram integration. Generate working code with live audio transcription and text-to-speech data.

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

Generate Code with Live Deepgram Data

Stop writing boilerplate for API calls. Tell Cursor's agent to transcribe an audio file using the `transcribe_url` tool. It won't just give you the text; it will generate the Python or JS code needed to make that exact API call, complete with the real response. This works for all the Deepgram tools. Ask it to 'generate code to create a new API key' and you'll get a working function that calls `create_key`. It’s the fastest way to go from an idea to production code that uses the Deepgram API.

Manage Keys and Projects from the Editor

You're in the middle of coding and need a new API key. Instead of switching to your browser, just ask the agent to `create_key`. It gets you a key instantly so you can drop it into your environment variables and keep working without breaking your flow. This MCP Server puts your entire Deepgram account admin inside your code editor. Use `get_usage` to see if you're hitting limits or `list_projects` to confirm a project ID.

Prototype Audio Features Inside Cursor

Building a feature that uses text-to-speech? Use the `speak_text` tool directly in Cursor to generate audio samples. You can test different voices or phrasing and hear the results immediately, which is much faster than running a full dev server. This turns your editor into a real-time audio lab. You're not just writing code; you're interacting with the live Deepgram service, making sure the audio output is exactly what you need before you commit a single line.

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-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

Enable Agent mode in Cursor and ask it to perform a Deepgram task, like transcribing audio. It will call the tool and then generate the code that made the API call. You get tested, working code that uses real API responses.

Yes, the MCP server gives you tools for key management (`create_key`), project listing (`list_projects`), and usage tracking (`get_usage`). You can run all your Deepgram admin tasks without leaving your editor.

Yes. Cursor's agent can generate code snippets for multiple languages. You can ask it to 'use `transcribe_url` and show me the code in Python' and it will do just that.

It's simple. You add the MCP Server configuration to a `mcp.json` file in your project or home directory. Once that's saved, the Deepgram tools are available to the agent in chat.

Your code and prompts are processed by Cursor, but this server only interacts with the Deepgram API on your behalf. It handles URLs for transcription and text for speech synthesis, but never stores them. The connection is ephemeral and your Deepgram credentials are not exposed.

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