pa-elevenlabs-mcp
A self-hosted HTTP MCP server wrapping the ElevenLabs speech-to-text API, enabling audio transcription with speaker diarization.
README
pa-elevenlabs-mcp
A self-hosted HTTP MCP server wrapping the ElevenLabs speech-to-text API. Designed to be used with Claude Cowork plugins where the sandbox blocks direct outbound API calls. The MCP server runs on the host machine (outside the sandbox), so the API call goes through cleanly.
Tools exposed
| Tool | Description |
|---|---|
speech_to_text |
Transcribe an audio file using ElevenLabs Scribe v2 with speaker diarization |
list_models |
List available ElevenLabs models |
Local development with Docker Compose + ngrok
1. Set up environment variables
cp .env.example .env
Edit .env and fill in:
ELEVENLABS_API_KEY=sk_...
NGROK_AUTHTOKEN=your_ngrok_authtoken # get free token at https://ngrok.com
2. Start the server
docker compose up --build
This starts:
mcp-serveron port8000ngroktunnel on port4040(inspect UI)
3. Get your ngrok public URL
curl -s http://localhost:4040/api/tunnels | python3 -m json.tool | grep public_url
Or open http://localhost:4040 in your browser.
You'll get a URL like: https://abc123.ngrok-free.app
4. Test the health endpoint
curl https://abc123.ngrok-free.app/health
# {"status":"ok"}
Connect to a Cowork plugin
Add the following to your plugin's .mcp.json (or to claude_desktop_config.json for Claude Code):
{
"mcpServers": {
"elevenlabs-mcp": {
"type": "http",
"url": "https://abc123.ngrok-free.app/mcp"
}
}
}
Replace abc123.ngrok-free.app with your actual ngrok URL.
In your skill, call the tool like:
Use the elevenlabs-mcp speech_to_text tool with:
- file_path: /absolute/path/to/audio.mp3
- model_id: scribe_v2
- diarize: true
EC2 production deployment
For production, use the same docker-compose.yml but:
- Remove the
ngrokservice entirely - Point your domain to port
8000using nginx or Caddy as a reverse proxy - Use HTTPS (Let's Encrypt via Caddy is the easiest option)
Minimal Caddyfile:
your-domain.com {
reverse_proxy localhost:8000
}
Update .mcp.json to use your real domain:
{
"mcpServers": {
"elevenlabs-mcp": {
"type": "http",
"url": "https://your-domain.com/mcp"
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.