Whatsapp MCP server

tr4m0ryp4stars

WhatsApp MCP server - Connect Claude to WhatsApp for reading and sending messages

1# Whatsapp

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: NOASSERTION
Last checked: 2026-10-28

Stars: 4
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Whatsapp?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Whatsapp need an API key?

No required environment variable is listed on this record.

What transport does Whatsapp use?

Whatsapp runs locally over stdio.

When was Whatsapp last checked?

Last checked 2026-10-28. WhatsApp MCP server - Connect Claude to WhatsApp for reading and sending messages

From the publisher

Documentation

whatsapp_mcp

An MCP server that puts your WhatsApp in your LLM's hands. Read, search, and send WhatsApp messages from your LLM — your chats become context it can actually use, and it can reply, react, and share files for you.

Under the hood it's two small processes. A Go bridge pairs with your phone once (QR scan, the official multi-device protocol) and quietly archives every chat into a local SQLite database, exposing a token-guarded loopback API for sending. A Python MCP server sits on top and gives the LLM 14 tools: search contacts and messages, list chats, send texts, quoted replies, reactions, files, and voice notes.

In short:

Run the bridge, scan the QR code once.
Point your MCP client at the server.
Ask things like "what did Anna say about the deposit?" or "send 'on my way' to +31 6 1234 5678".

Everything stays on your machine: messages live in local SQLite, the model only sees what a tool call returns, and the send API is loopback-only behind a bearer token. The usual caution applies — an LLM that can read and send your messages is a prompt-injection target, so use it with awareness.

License

MIT — see LICENSE. This is a ground-up restructure of tr4m0ryp/whatsapp-mcp, itself a maintained fork of lharries/whatsapp-mcp; the original copyright notices travel with it.