Provides voice synthesis capabilities to generate audio responses using ElevenLabs text-to-speech API for mood-based interactions.
Enables LLM-powered mood classification and natural language processing for analyzing user messages.
Fetches curated playlists based on detected user mood using Spotify's API to provide personalized music recommendations.
Handles inbound and outbound WhatsApp/SMS messages through webhook integration, enabling message-based interactions with mood detection and playlist delivery.
Processes WhatsApp messages to detect user mood and respond with personalized playlists, quotes, and optional voice notes.
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., "@Mood-Based Music & Quote MCP Server I'm feeling anxious today, can you suggest some calming music?"
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.
An MCP-style server that reacts to WhatsApp/SMS messages: it classifies the user's mood, fetches a curated Spotify playlist, adds a motivational/funny quote, and can optionally deliver a voice note (ElevenLabs). Includes Twilio webhook for inbound WhatsApp and simple MCP endpoints for tool calls.
Install deps
npm installCopy env template
cp config/env.example .envFill in Spotify client credentials, Twilio (for WhatsApp/SMS), and optional ElevenLabs + OpenAI.
Run dev server
npm run devRelated MCP server: Spotify MCP Server
GET /healthz – health check
GET /mcp/tools – list available tools
POST /mcp/call – invoke a tool: { "name": "run_mood_flow", "input": { "to": "whatsapp:+1...", "text": "I feel stressed", "includeVoice": false } }
POST /webhooks/twilio – Twilio WhatsApp/SMS webhook; echoes back playlist + quote
detect_mood
get_playlist
get_quote
synthesize_voice (if ElevenLabs configured)
send_message
run_mood_flow (end-to-end orchestration)
Voice replies require hosting the MP3 somewhere accessible; the current stub generates audio but does not upload it. Add an object-store upload to send MediaUrl with Twilio.
Mood classification defaults to a keyword heuristic; plug in an LLM if desired.
MCP shape here is HTTP-based for simplicity; can be adapted to an MCP transport.
This server cannot be deployed
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted.
ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.