Connects to a WhatsApp account as a linked device, allowing AI assistants to read, search, and send messages across chats. Supports listing and finding chats and people, retrieving message history and context, searching all messages, sending replies or mentions, reacting to, editing, and deleting messages, marking chats as read, managing contacts, loading older history, checking WhatsApp numbers, and viewing group and profile information.
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., "@whatsapp-mcp tell the family group I'll be late"
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.
Give your AI agents your WhatsApp.
whatsapp-mcp lets an AI assistant like Claude read your WhatsApp chats, search them and send messages for you. It connects to your account the same way WhatsApp Web does, as a linked device, and keeps a searchable copy of your chats.
It speaks MCP, the standard way AI apps connect to tools, so it works with Claude, ChatGPT, Claude Code, Cursor and other MCP clients. It runs on your own Cloudflare account, so your messages stay with you.
Once it is set up, you ask in plain words and your assistant calls the tools for you:
You need a Cloudflare account, a GitHub account and your phone with WhatsApp.
Click Deploy to Cloudflare above. Cloudflare copies this project to your GitHub, builds it and puts it online at an address like https://whatsapp-mcp.<your-name>.workers.dev.
During the setup it asks for a SECRET. That is the password of your server, at least 16 characters. Generate a strong one in a terminal with openssl rand -hex 32, or use a password manager, and keep it safe. Anyone who has it can read and send your messages.
Open this address in your browser and sign in with your SECRET:
https://whatsapp-mcp.<your-name>.workers.dev/accounts/personalSelect Link WhatsApp. On your phone, open WhatsApp, go to Settings → Linked devices → Link a device and point the camera at the code. The page then counts your chats as they arrive.
personal is a name you choose. Each name is a separate WhatsApp account, so one server can hold several.
Add this address as a custom connector in Claude or ChatGPT, or as a remote MCP server in any other client:
https://whatsapp-mcp.<your-name>.workers.dev/accounts/personal/mcpThe app opens your server in the browser. Sign in with your SECRET and select Allow. In Claude Code that is:
claude mcp add --transport http whatsapp https://whatsapp-mcp.<your-name>.workers.dev/accounts/personal/mcpIn pi, add it and sign in from the terminal:
pi mcp add whatsapp --url https://whatsapp-mcp.<your-name>.workers.dev/accounts/personal/mcp
pi mcp login whatsappScripts and clients that can set a header can skip the browser and send Authorization: Bearer <SECRET> instead.
Related MCP server: WhatsApp MCP Server
Tool | What it does |
| Connection state and how much of your history is saved |
| Chats in the order your phone shows them, with unread counts |
| Chats by any name or phone number |
| People by any name or phone, including group members |
| A chat's messages, with paging and date or sender filters |
| A message and the conversation around it |
| Search all chats by words, ignoring accents and capitals |
| Sends text, as a reply or with mentions, never twice on retries |
| Adds or removes a reaction |
| Edits a message you sent |
| Deletes a message for everyone |
| Marks a chat as read |
| Saves or renames someone in your address book, on every device |
| Removes someone from your address book, on every device |
| Asks your phone for older history |
| Which phone numbers have WhatsApp |
| A group's details and members |
| Someone's name, About text and picture |
Tools that send or change something tell your assistant so, and most assistants ask you before using them.
flowchart LR
agent["AI assistant"] -- "MCP + OAuth" --> worker["Worker"]
worker -- "RPC" --> account
subgraph account["Durable Object, one per WhatsApp account"]
socket["WhatsApp session<br/>whatsapp-rust in WASM"]
archive[("SQLite archive<br/>full-text search")]
socket --> archive
end
socket <-- "WebSocket" --> whatsapp["WhatsApp"]Each WhatsApp account lives in its own Durable Object, a small server that Cloudflare keeps running with its own SQLite database. The WhatsApp session inside it is baileyrs, whose protocol core is whatsapp-rust compiled to WebAssembly. An alarm every 30 seconds keeps the object in memory and reconnects it after deploys.
WhatsApp sends your recent history once, when you link, and the archive keeps every message after that. Search finds people by any name they have used, and treats a person's phone number and their anonymous WhatsApp ID (LID) as the same person.
Name | Kind | Purpose |
| Secret | The password of your server, at least 16 characters |
| Variable | How MCP clients get in: |
| Variable | Time zone for dates, like |
With oauth, an app connects after you sign in with SECRET in the browser and allow it. With api_key, clients send Authorization: Bearer <SECRET> on every request. The pairing page asks for SECRET in every mode, and allows five attempts per minute.
Change the variables in wrangler.jsonc, or pass --var TIMEZONE:<zone> to wrangler deploy. OAuth grants live in a KV namespace that the first deploy creates. The pairing page also uses a small REST API under /accounts/:id: status, start, send and logout.
One personal account running 24/7 costs $5 per month, the price of Workers Paid. Its included usage covers everything one account does:
One account, per month | Workers Paid includes | |
Time in memory | 324,000 GB-s | 400,000 GB-s |
Requests | 90,000, plus your assistant's calls | 1 million |
Written rows | 260,000 once to link, then 90,000 plus new messages | 50 million |
The object stays in memory all day, and Cloudflare bills that time as if it used the full 128 MB, however busy the account is. It also wakes every 30 seconds, which explains the 90,000 requests and rows. Linking saves the whole history at once: an account with about 30,000 messages wrote 258,000 rows in its first hour. Going past the included usage would take about 30,000 assistant calls or 100,000 new messages a day.
More accounts share the same plan. Cloudflare bills extra time in blocks of 1 million GB-s at $12.50, so two to four accounts cost $17.50 per month.
Workers Free is not enough, even for one account.
Workers Free allows 100,000 written rows per day, fewer than the first sync writes. When an account crosses that limit, Cloudflare blocks every write until 00:00 UTC, so the server can't save new messages or schedule its heartbeat. Upgrading to Workers Paid lifts the block.
See Workers pricing, Durable Objects pricing and limits for current numbers.
Your session and your messages stay in your Cloudflare account. The server talks only to WhatsApp, and only someone who knows your SECRET can use it or allow an app in.
This is an unofficial WhatsApp client, not affiliated with WhatsApp or Meta, and WhatsApp can ban accounts that use one. Link a number you can afford to lose, and keep your assistant asking before it sends messages.
You need Bun. Wrangler comes with the project.
bun install
printf 'SECRET=%s\n' "$(openssl rand -hex 32)" > .dev.vars # see .dev.vars.example
bun run dev # http://localhost:8787/accounts/dev
bun run check # types, lint, format and testsTo deploy from your machine, run bunx wrangler secret put SECRET once and then bun run deploy.
Built on baileyrs and whatsapp-rust. Message rendering and identity rules follow mautrix-whatsapp. Licensed under GPL-3.0.
This server cannot be deployed
Read, search and reply to your WhatsApp chats from your AI, using your own number.
WhatsApp for Claude, ChatGPT or any AI agent: search, reply and send. Personal or Business API.
Your own WhatsApp in Claude and ChatGPT: read chats, draft replies, send messages you approve.
WhatsMCP connects Claude and other MCP-compatible AI agents directly to WhatsApp. Send and receive text, images, documents, and voice notes; manage groups (create, add/remove members, promote admins); look up contacts and profiles; follow channels; and read call and message history — all through a standard MCP interface. For voice use cases, WhatsMCP offers SIP-based calling plans (inbound-only, or full inbound/outbound) so AI voice agents can answer and place WhatsApp calls, plus low-latency WebSocket integrations with voice agent providers like ElevenLabs. Multiple WhatsApp accounts can be paired and managed per workspace, with webhook support for real-time inbound message delivery to your own infrastructure.
