zaileys-mcp
Enables AI agents to control WhatsApp, including sending messages and media, reading chats, managing groups and communities, with QR/pairing auth and session persistence.
README
<div align="center">
<br>
<img alt="zaileys-mcp — WhatsApp for AI agents, powered by Zaileys" src="https://github.com/zeative/zaileys-mcp/blob/main/public/icon.png?raw=true" width="130">
<br> <br>
<h1 align="center">zaileys-mcp — WhatsApp for AI agents, <br /> powered by Zaileys</h1>
<br>
<div align="center"> <a href="https://www.npmjs.com/package/zaileys-mcp"><img src="https://img.shields.io/npm/v/zaileys-mcp.svg" alt="NPM Version"></a> <a href="https://www.npmjs.com/package/zaileys-mcp"><img src="https://img.shields.io/npm/dw/zaileys-mcp?label=npm&color=%23CB3837" alt="NPM Downloads"></a> <a href="https://github.com/zeative/zaileys-mcp/releases"><img src="https://img.shields.io/npm/dt/zaileys-mcp" alt="NPM Total Downloads"></a> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-server-6E56CF" alt="MCP Server"></a> </div>
<div align="center"> <a href="https://github.com/zeative/zaileys-mcp/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="License: MIT"></a> <a href="https://discord.gg/KBHhTTVUc5"><img alt="Discord" src="https://img.shields.io/discord/1105833273415962654?logo=discord&label=discord"></a> <a href="https://chat.whatsapp.com/GlQfvc83mSH3F6ov06vuCt"><img alt="WhatsApp" src="https://img.shields.io/badge/WhatsApp-Group-25D366?logo=whatsapp&logoColor=white"></a> <a href="https://github.com/zeative/zaileys-mcp"><img src="https://img.shields.io/github/stars/zeative/zaileys-mcp" alt="GitHub Stars"></a> <a href="https://github.com/zeative/zaileys-mcp"><img src="https://img.shields.io/github/forks/zeative/zaileys-mcp" alt="GitHub Forks"></a> </div>
<br>
<div align="center"> <p> <b>zaileys-mcp</b> is a <a href="https://modelcontextprotocol.io">Model Context Protocol</a> server that gives AI agents — Claude, Cursor, any MCP client — the ability to drive WhatsApp: send messages, media, polls, and locations; read chats and history; manage groups, communities, newsletters, contacts, presence, and profile. Powered by <a href="https://github.com/zeative/zaileys">Zaileys</a>, so QR / pairing-code auth, reconnection, and sessions are handled for you. </p> </div>
<div align="center">
Quick start • Why zaileys-mcp • Install • What you can build • Configuration • Docs
</div>
</div>
<br>
[!NOTE] This README is a high-level overview. The complete guides, tool catalog, and configuration reference live in the documentation site at https://zeative.github.io/zaileys-mcp/.
[!WARNING] This drives a real WhatsApp account through the unofficial Web API (via Zaileys/Baileys). WhatsApp may suspend numbers that use unofficial automation, and an AI agent with these tools can message anyone in your account. Use
read-onlyor an allowlist when you don't need full access, and never point it at an account you can't afford to lose.
Quick start
Add it to your MCP client — npx fetches it on demand. First launch prints a QR to scan in WhatsApp → Linked Devices; the session persists.
{
"mcpServers": {
"whatsapp": {
"command": "npx",
"args": ["-y", "zaileys-mcp"],
"env": { "ZAILEYS_SESSION": "my-wa" }
}
}
}
That's it. Restart your client, then ask your agent:
"Send a WhatsApp to +62 812 3456 7890 that the deploy is done ✅"
"Summarize my last 20 messages in the family group."
Works with Claude Desktop, Cursor, and any MCP client that speaks stdio.
Why zaileys-mcp
- Full 1:1 with Zaileys — 60+ tools covering messaging, chats, groups, communities, newsletters, privacy, profile, presence, contacts, and business. Anything Zaileys can do, an agent can do.
- Smart tool strategy — all 60+ tools exist, but only a small core stays in the agent's context; the rest are revealed on demand via a
find_toolsmeta-tool. Full capability, small context — no bloating every request. - Zero-config auth — Zaileys handles the WhatsApp connection. First run prints a QR; the session persists, restarts connect silently.
- Embeddable — already run a Zaileys bot? Expose it to AI agents in one line; it reuses your live session, no second login.
- Safe by design —
read-onlymode and recipient allowlists for when an agent shouldn't have full reach. - Clean transport — stdio JSON-RPC stays uncorrupted; QR and logs go to stderr. Custom HTTP/SSE transport supported.
Install
No install needed for the standalone server — npx handles it:
npx -y zaileys-mcp
To embed it in your own bot, add it as a dependency:
npm i zaileys-mcp zaileys # or: pnpm add • yarn add • bun add
Requires Node.js v20+. Peer dependency: zaileys >= 4.7.
What you can build
Drive WhatsApp from your agent
60+ tools, 1:1 with the Zaileys API — every to / chat / jid accepts a phone number or a JID interchangeably.
Agent: "add +62 811 111 111 to the Weekend group and make them admin"
→ find_tools("add member to group") → enables group_add, group_promote, …
→ group_add({ group, participants })
→ group_promote({ group, participants })
<details> <summary><b>Full tool catalog</b></summary>
- Messaging —
send_text,send_media,send_location,send_poll,send_contact,send_sticker,react,edit_message,delete_message,forward_message,pin_message,unpin_message - Chats —
list_chats,get_messages,chat_archive/unarchive/pin/unpin/mute/unmute/mark_read/mark_unread/delete/clear,set_disappearing - Account & contacts —
me,check_number,get_profile,save_contact,remove_contact - Presence —
send_typing,send_recording,set_presence - Groups —
group_metadata/list/create/add/remove/promote/demote/update_subject/update_description/leave/invite_code/invite_revoke/invite_info/invite_accept/join_requests/approve_join/reject_join/setting/join_approval/member_add_mode/toggle_ephemeral - Communities —
community_metadata/list/subgroups/create/link_group/unlink_group/leave - Newsletters —
newsletter_metadata/messages/create/follow/unfollow/mute/unmute/react - Privacy —
privacy_get,blocklist,block,unblock - Profile —
set_profile_name/status/picture,remove_profile_picture - Business —
business_profile,business_catalog,business_collections
</details>
Smart tool strategy
60+ tools is a lot to inject into an agent's context on every request. zaileys-mcp uses progressive tool disclosure (the default): only a small core (~13 tools) stays active, and the rest are revealed on demand via a find_tools meta-tool that enables matches and fires MCP's tools/list_changed.
ZAILEYS_TOOLS=progressive # ~13 core active, rest via find_tools (default)
ZAILEYS_TOOLS=full # all 60+ active
ZAILEYS_TOOLS=core # ~12 core, no discovery
ZAILEYS_TOOLS=send_text,get_messages # a hand-picked set (+ find_tools)
Embed in your own bot
Already run a Zaileys client? Expose it to AI agents in one line — it reuses your live session:
import { Client } from 'zaileys'
import { serveMcp } from 'zaileys-mcp'
const client = new Client()
await serveMcp(client) // AI agents can now drive this WhatsApp over stdio
Read-only, allowlist, or a custom transport:
import { createMcpServer, serveMcp } from 'zaileys-mcp'
await serveMcp(client, { readOnly: true, allowlist: ['62812xxxxxxx'] })
const server = createMcpServer(client) // bring your own HTTP/SSE transport
await server.connect(myHttpTransport)
Configuration
Standalone (env vars) — programmatic options mirror these one-to-one:
| Variable | Default | Description |
|---|---|---|
ZAILEYS_SESSION |
mcp |
Session id (auth persists under ./.zaileys/auth/<id>) |
ZAILEYS_AUTH_TYPE |
qr |
qr or pairing |
ZAILEYS_PHONE |
— | Phone number (E.164 digits) for pairing-code login |
ZAILEYS_READONLY |
false |
true exposes only read tools (agent can't send) |
ZAILEYS_ALLOWLIST |
— | Comma-separated numbers/JIDs; restricts outbound tools |
ZAILEYS_TOOLS |
progressive |
progressive · full · core · comma-list |
Two guardrails, usable in any mode: readOnly (write tools never registered) and allowlist (outbound tools refuse other recipients). Recommended: readOnly for summarizers/monitors, allowlist for personal/team notifiers, a dedicated number for full automation.
Documentation
- 🌐 zeative.github.io/zaileys-mcp — full documentation: getting started, tools, tool strategy, safety
- ⚙️ zeative.github.io/zaileys — the WhatsApp engine underneath
- 🔌 Model Context Protocol — the MCP standard
Issues & feedback
Hit a problem or have a feature request? Open an issue.
- Buy me a coffee ☕ • Ko-Fi • Trakteer
- ⭐ Star the repo on GitHub
License
Distributed under the MIT License. See LICENSE for details.
<div align="left"> <p> <img alt="zaileys-mcp" src="https://github.com/zeative/zaileys-mcp/blob/main/public/icon.png?raw=true" width="28" align="center"> Copyright © 2026 zaadevofc. All rights reserved. </p> </div>
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.