Skip to content

Summary

Deepgram's official MCP server, bringing speech-to-text, text-to-speech and audio intelligence into Claude Code, Cursor and Windsurf.

Features

  • Speech-to-text, text-to-speech and audio intelligence tools inside the editor
  • Tool list fetched from the Deepgram API at runtime — new tools appear without upgrading the package
  • stdio or SSE transport, with host, port and base-URL flags
  • Single DEEPGRAM_API_KEY environment variable; free key available from the console

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "Deepgram" tools will be available.
{
  "mcpServers": {
    "deepgram-mcp": {
      "command": "deepgram-mcp",
      "env": {
        "DEEPGRAM_API_KEY": "your_api_key_here"
      }
    }
  }
}

Description

Deepgram's official MCP server connects a coding agent to Deepgram's speech platform — transcription, text-to-speech and audio intelligence — so audio work happens inside the editor rather than through a side script.

The design choice worth noting

The tool list is fetched from the Deepgram API at runtime, not compiled into the package. New Deepgram capabilities appear in your editor the next time you connect, with no package upgrade — a pragmatic answer to the usual problem of MCP servers drifting behind the API they wrap.

Setup

Install from PyPI and set one environment variable:

pip install deepgram-mcp
{
  "mcpServers": {
    "deepgram": {
      "command": "deepgram-mcp",
      "env": { "DEEPGRAM_API_KEY": "your_api_key_here" }
    }
  }
}

A free API key is available from the Deepgram console. The server also accepts --transport (stdio or sse), --port, --host, --base-url and --debug, so it can be run as a network service as well as a local subprocess.

Requirements

Python with pip, and a Deepgram API key. Published under the MIT licence.

Related MCP Servers

New

Replicate's official MCP server: search thousands of hosted models, read their schemas, and run predictions on image, video, audio and language models from inside an agent.

MCP: Hugging Face

by Hugging Face

New

Hugging Face's official remote MCP server — search and inspect models, datasets and Spaces, browse the Hub filesystem over hf:// URIs, and turn Gradio Spaces into callable tools.

MCP: Resend

by Resend

New

Resend's official MCP server for transactional and marketing email — send, schedule and batch messages, manage templates, contacts, broadcasts, automations, domains and suppressions from an agent.

New

Postman's official MCP server — reach your workspaces, collections, specs and environments from Claude Code, Cursor, VS Code or Copilot, in four tool tiers.

Browse all MCP servers →