WhatsApp LLM
A WhatsApp bot that can participate in group conversations, powered by AI. The bot monitors group messages and responds when mentioned.
What is WhatsApp LLM?
WhatsApp LLM is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to whatsapp bot that can participate in group conversations, powered by ai. the bot monitors group messages and responds when mentioned.
A WhatsApp bot that can participate in group conversations, powered by AI. The bot monitors group messages and responds when mentioned.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A WhatsApp bot that can participate in group conversations,
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx wa-llmConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use WhatsApp LLM
WhatsApp LLM (wa_llm) is a self-hosted WhatsApp bot that monitors group conversations and responds intelligently when mentioned, powered by Claude AI via the Anthropic API. It uses vector embeddings and PostgreSQL to maintain conversation context, can generate AI-powered summaries of group discussions, and provides a REST API for triggering summaries and loading knowledge base topics. Users deploy it to add an AI assistant to WhatsApp groups without sharing access to a third-party service.
Prerequisites
- Docker and Docker Compose installed (recommended deployment method)
- An Anthropic API key (format: sk-ant-...) for Claude AI responses
- A Voyage AI API key for vector embeddings (VOYAGE_API_KEY)
- A PostgreSQL database accessible via connection string
- A WhatsApp account to authenticate the bot via QR code scan
Clone the repository
Clone the wa_llm repository to your server or local machine.
git clone https://github.com/ilanbenb/wa_llm.git
cd wa_llmConfigure environment variables
Copy the example environment file and fill in your credentials. All required keys must be set before starting the containers.
cp .env.example .env
# Edit .env with your values:
# ANTHROPIC_API_KEY=sk-ant-your-key
# VOYAGE_API_KEY=your-voyage-key
# DB_URI=postgresql://user:password@host:5432/dbname
# WHATSAPP_HOST=http://localhost:3000
# WHATSAPP_BASIC_AUTH_USER=admin
# WHATSAPP_BASIC_AUTH_PASSWORD=your-passwordStart the services with Docker Compose
Launch all services (WhatsApp Web API, bot, and database) using Docker Compose for development.
docker compose up -dScan the WhatsApp QR code
Open a browser and navigate to localhost:3000 to see the WhatsApp Web QR code. Scan it with the WhatsApp app on your phone (Settings → Linked Devices → Link a Device) to authenticate the bot.
Activate the bot for specific WhatsApp groups
After authentication, use the PostgreSQL database to set 'managed = true' for the WhatsApp groups you want the bot to monitor. Only groups with this flag enabled will receive bot responses and summaries.
Verify the bot is working
Mention the bot in a managed WhatsApp group. It should respond using Claude AI. You can also trigger a summary via the REST API.
# Trigger a group summary via REST API:
curl -X POST http://localhost:8000/trigger_summarize_and_send_to_groupsWhatsApp LLM Examples
Client configuration
This server is a standalone WhatsApp bot, not a typical MCP server added to a client config. Below is the .env configuration structure for deployment.
{
"mcpServers": {
"wa-llm": {
"command": "npx",
"args": ["wa-llm"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-your-key",
"VOYAGE_API_KEY": "your-voyage-api-key",
"DB_URI": "postgresql://user:password@localhost:5432/wa_llm",
"WHATSAPP_HOST": "http://localhost:3000",
"WHATSAPP_BASIC_AUTH_USER": "admin",
"WHATSAPP_BASIC_AUTH_PASSWORD": "your-password",
"LOG_LEVEL": "INFO"
}
}
}
}Prompts to try
Interact with the bot in a WhatsApp group by mentioning it, or use the REST API endpoints for automation.
- Mention the bot in a group: "@bot can you summarize what we discussed today?"
- "@bot what did we decide about the project deadline?"
- REST API: POST /load_new_kbtopic to load a knowledge base topic for informed answers
- REST API: POST /trigger_summarize_and_send_to_groups to push a summary to all managed groups
- DM the bot 'opt-out' to disable summary notifications for your accountTroubleshooting WhatsApp LLM
QR code does not appear at localhost:3000
Ensure the WhatsApp Web API container started successfully by checking 'docker compose logs'. The WHATSAPP_HOST variable should match the container's network address. If running on a remote server, forward port 3000 via SSH tunneling: 'ssh -L 3000:localhost:3000 user@server'.
Bot does not respond in WhatsApp groups
Verify that the group has 'managed = true' in the PostgreSQL database. Check ANTHROPIC_API_KEY is valid and has available quota. Review logs with LOG_LEVEL=DEBUG to see incoming message processing and any API errors.
Vector embedding or similarity search fails
VOYAGE_API_KEY must be set and valid for the Voyage AI embedding service. Verify the PostgreSQL database has the pgvector extension installed. Check DB_URI is correct and the database is reachable from the Docker network.
Frequently Asked Questions about WhatsApp LLM
What is WhatsApp LLM?
WhatsApp LLM is a Model Context Protocol (MCP) server that whatsapp bot that can participate in group conversations, powered by ai. the bot monitors group messages and responds when mentioned. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install WhatsApp LLM?
Follow the installation instructions on the WhatsApp LLM GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with WhatsApp LLM?
WhatsApp LLM works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is WhatsApp LLM free to use?
Yes, WhatsApp LLM is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
WhatsApp LLM Alternatives — Similar Communication Servers
Looking for alternatives to WhatsApp LLM? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up WhatsApp LLM in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use WhatsApp LLM?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.