WhatsApp MCP Server
Connect your personal WhatsApp to Claude — send messages, read chats, and manage contacts.
README
WhatsApp MCP Server
Connect your personal WhatsApp to Claude — send messages, read chats, and manage contacts.
How it works
Claude ←→ Python MCP server (server.py)
↕ HTTP localhost:3000
Node.js WhatsApp bridge (whatsapp-bridge/)
↕ WhatsApp Web protocol
Your personal WhatsApp
Prerequisites
| Tool | Download |
|---|---|
| Node.js ≥ 18 | https://nodejs.org |
| Python ≥ 3.10 | https://python.org |
| Google Chrome | (already installed on most machines) |
One-time setup
Step 1 — Install bridge dependencies
Open a terminal in this folder and run:
cd whatsapp-bridge
npm install
Step 2 — Install Python dependencies
pip install -r requirements.txt
Every-time usage
Step 1 — Start the WhatsApp bridge
Double-click start_bridge.bat (or run in a terminal):
cd whatsapp-bridge
node index.js
A QR code will appear. On your phone:
- Open WhatsApp → Settings → Linked Devices → Link a Device
- Scan the QR code
The terminal will show 🟢 WhatsApp bridge ready when connected.
Keep this terminal open while using Claude. If you close it, Claude loses access to WhatsApp.
Step 2 — Connect Claude to the MCP server
Add the following to your Claude Desktop config file:
Config file location:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"whatsapp": {
"command": "python",
"args": ["C:\\Users\\pc\\Claude\\Projects\\Whatsup MCP\\server.py"]
}
}
}
Replace the path if you moved this folder.
Step 3 — Restart Claude Desktop
After saving the config, fully quit and reopen Claude Desktop. You should see a 🔌 WhatsApp connection in the tools panel.
Available tools
| Tool | What it does |
|---|---|
whatsapp_get_status |
Check connection state |
whatsapp_list_chats |
List recent conversations |
whatsapp_get_messages |
Read messages from a chat |
whatsapp_list_contacts |
List your contacts |
whatsapp_send_message |
Send a text message |
Example prompts for Claude
- "Show my recent WhatsApp chats"
- "Read the last 10 messages from Priya"
- "Send 'On my way!' to Rahul on WhatsApp"
- "List all my WhatsApp group chats"
Troubleshooting
"Cannot reach the WhatsApp bridge"
→ Make sure start_bridge.bat is running and shows 🟢 WhatsApp bridge ready.
QR code expired
→ Restart the bridge — a new QR will appear. You only need to scan once per session (auth is saved in whatsapp-bridge/.wwebjs_auth).
"puppeteer" / Chrome error on startup
→ Make sure Google Chrome is installed. If you have a custom Chrome path, add this to whatsapp-bridge/index.js inside the puppeteer block: executablePath: 'C:\\Path\\To\\chrome.exe'
Messages not sending
→ Use whatsapp_list_contacts to get the correct chat ID, then pass that ID to whatsapp_send_message.
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.