Provides tools for speech-to-text transcription, speech recognition, and audio intelligence operations through the Deepgram API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Deepgram MCP transcribe the interview.mp3 file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Deepgram's Model Context Protocol server — gives AI editors (Claude Code, Cursor, Windsurf, and others) direct access to Deepgram's speech, transcription, and audio intelligence tools.
Standalone package. Install deepgram-mcp directly if you want just the MCP server without the full CLI suite. If you already use the Deepgram CLI (pip install deepctl), deepgram-mcp is included as a dependency and the dg mcp command wraps it — no separate install needed.
Most MCP servers ship tools as hardcoded Python. When the provider adds a new tool, you must upgrade the package to get it.
deepgram-mcp fetches its tool list from Deepgram's API at runtime. New tools appear in your editor the next time you connect — no package upgrade required.
Related MCP server: Whissle MCP Server
A Deepgram API key. Get one free at console.deepgram.com.
Set it as an environment variable:
export DEEPGRAM_API_KEY=your_api_key_herepip install deepgram-mcpAdd to .mcp.json in your project root (or ~/.claude/mcp.json for global):
{
"mcpServers": {
"deepgram": {
"command": "deepgram-mcp",
"env": {
"DEEPGRAM_API_KEY": "your_api_key_here"
}
}
}
}Or via CLI:
claude mcp add deepgram -- deepgram-mcpAdd to .cursor/mcp.json:
{
"mcpServers": {
"deepgram": {
"command": "deepgram-mcp",
"env": {
"DEEPGRAM_API_KEY": "your_api_key_here"
}
}
}
}Add to your Windsurf MCP config:
{
"mcpServers": {
"deepgram": {
"command": "deepgram-mcp",
"env": {
"DEEPGRAM_API_KEY": "your_api_key_here"
}
}
}
}deepgram-mcp --api-key your_api_key_heredeepgram-mcp --transport sse --port 8000Flag | Default | Description |
|
| Transport mode: |
|
| Port for SSE server |
|
| Host for SSE server |
|
| Deepgram API key |
|
| Deepgram developer API base URL |
|
| Print debug info to stderr |
import asyncio
from deepgram_mcp import run_proxy
asyncio.run(run_proxy(
transport="stdio",
host="127.0.0.1",
port=8000,
api_key="your_api_key_here",
base_url="https://api.dx.deepgram.com",
debug=False,
))If you use the Deepgram CLI, dg mcp wraps this package and handles authentication automatically:
dg mcp
dg mcp --transport sse --port 8000MIT — see LICENSE.
This server cannot be deployed
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
Edit video by talking to your AI — search footage, cut timelines, apply effects, add captions.
Transcribe audio & video to text for AI agents: 100+ languages, speaker labels, webhooks.
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
