What is whatsapp-mcp?

The WhatsApp MCP Server connects to your personal WhatsApp account via the WhatsApp web multidevice API, storing messages locally in SQLite. It enables searching, reading, and sending messages to individuals or groups, along with media handling, through an LLM agent like Claude using standardized MCP tools.

whatsapp-mcp: The WhatsApp MCP Server connects to your personal WhatsApp account via… (★ 5.9k, MIT)

Features

01Search and read personal WhatsApp messages (text, media)

02Search contacts and send messages to individuals/groups

03Send various media types (images, videos, documents, audio)

04Local message storage in a SQLite database

05Integrates with LLMs (e.g., Claude) via MCP tools

Why choose it

+Search and read personal WhatsApp messages (text, media)

+Leveraging LLMs (e.g., Claude) to interact with WhatsApp messages and contacts.

+Ships with a public repository and a MIT license, which makes adoption and review easier.

+The latest recorded update is 2025-07-13, which suggests the project is still actively maintained.

Trade-offs

!Compatibility coverage looks narrow, so it is worth validating your target runtime before committing to it.

!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.

Compatibility

Claude Desktop

Native

Verified via docs

Cursor

Native

Verified via docs

Quick start

$ git clone https://github.com/lharries/whatsapp-mcp.git

Use cases

↳Leveraging LLMs (e.g., Claude) to interact with WhatsApp messages and contacts.

↳Automated searching and retrieval of specific WhatsApp messages and chat history.

↳Sending messages and various media types to WhatsApp contacts or groups programmatically.

How it compares

≈whatsapp-mcp sits in the Voice / Speech category, so it makes more sense to evaluate it alongside tools like OpenClaw instead of in isolation.

≈If your main need is closer to "Leveraging LLMs (e.g., Claude) to interact with WhatsApp messages and contacts.", that use case is a better lens for comparison than broad feature checklists alone.

≈whatsapp-mcp uses a MIT license, and community traction are both easier to judge in category context.