# lharries/whatsapp-mcp

WhatsApp MCP server

Repository: https://github.com/lharries/whatsapp-mcp
Canonical: https://ross.abutalabs.com/products/whatsapp-mcp
Homepage: https://x.com/LukeHarries_/status/1905986562388635913
Language: Go
License: MIT
License Family: permissive
Topics: ai, mcp, whatsapp, whatsapp-api
Last push: 2025-07-13T17:22:00+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 31, release rhythm 8, longevity 37
- inputs: {"age_days": 522, "days_push": 416, "days_rel": 514, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6196, forks 1269 (observed 2026-08-28T04:09:39.534141+00:00)

## What it is
A Model Context Protocol (MCP) server that connects an LLM agent like Claude Desktop or Cursor to a personal WhatsApp account via the WhatsApp web multidevice API. It stores messages locally in SQLite and exposes tools to search/read messages and contacts and send text or media to individuals and groups.

## Use cases
- let Claude search and read my WhatsApp messages
- send WhatsApp messages to individuals or groups from an AI assistant
- query my WhatsApp chat history with an LLM
- search WhatsApp contacts from Claude Desktop
- send images, videos, documents, or voice notes to WhatsApp via an agent
- connect WhatsApp to Cursor as an MCP tool

## When to choose
- you use Claude Desktop or Cursor and want your personal WhatsApp accessible as agent tools
- you want messages stored locally in SQLite rather than in a cloud service
- you need to send or read media (images, video, documents, audio) through WhatsApp programmatically

## When to avoid
- you need an official WhatsApp Business API integration for production apps
- you cannot accept the prompt-injection data-exfiltration risk of exposing private messages to an LLM
- you need a long-lived unattended integration, since re-authentication via QR scan is required roughly every 20 days

## Facets
- artifact type: service
- maturity: active
- function: mcp, chatbot, search-engine, database
- domain: messaging-platforms, large-language-models, developer-tools
- platform: go, python, windows, cross-platform
- tags: whatsapp, model-context-protocol, claude-desktop, sqlite, whatsmeow, personal-messaging, llm-tools, ai-agents, macos, linux

## Member repositories
- lharries/whatsapp-mcp (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:39.534141+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:47:21.031068+00:00, confidence not recorded.
  - readme: https://github.com/lharries/whatsapp-mcp (fetched 2026-08-28T04:09:39.534141+00:00, sha ae5800c25328)
- Data as of 2026-08-30T08:39:29.467469+00:00.