# lharries/whatsapp-mcp

> An MCP server for WhatsApp: connects your personal account via the WhatsApp Web API, stores chats in a local SQLite database, and gives an LLM agent tools to search, read, and send messages and media.

- Magnitude: 2.4 out of 10 — Steady
- Stars: 6,372 total · +8 stars today, ≈ 15 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: MIT · Created: 2025-03-29 · Last push: 2025-07-13
- GitHub: https://github.com/lharries/whatsapp-mcp · Homepage: https://x.com/LukeHarries_/status/1905986562388635913 · Page: https://gitnova.dev/en/r/lharries/whatsapp-mcp

## Useful for

- Connect a personal WhatsApp account to Claude Desktop or Cursor via MCP
- Search message history or contacts through an LLM agent
- Send a message, file, or voice note to a chat or group from an LLM agent

## Why it’s here

- 8 stars so far today, about 15 expected by the end of the day. The usual pace is 5 per day, so that's 3.2× as much.
- Over the last two days the pace is 4.5× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- GitHub Trending Go today: #3, +24 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,352
- Issues and pull requests: 362
- Watchers: 53
- Average over the last week: 10 per day
- Usual pace: 5 per day
- Stars in the last hour (measured): 0
- Latest release: v0.0.1 (2025-04-06)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-03 … 2026-10-02: 4, 9, 3, 0, 5, 5, 6, 4, 3, 1, 10, 5, 6, 3, 2, 3, 3, 3, 11, 2, 7, 5, 0, 6, 4, 4, 2, 14, 23, 8

## Spotted in now

- GitHub Trending Go today: #3, +24 stars

## Similar by description

1. **wwebjs/whatsapp-web.js** — 1.3 · Steady · Backend & databases · JavaScript · +2 stars today, ≈ 4 by evening
   A Node.js library for interacting with WhatsApp Web via Puppeteer: send and receive messages, media, manage groups and contacts, and build bots or APIs on top of the web client.
   Full card: https://gitnova.dev/en/r/wwebjs/whatsapp-web.js.md
2. **Rion-Wu-tech/wechat-intelligence-hub** — 1.4 · Steady · Productivity & self-hosted · Python · +2 stars today, ≈ 4 by evening
   Local-first WeChat intelligence system that turns chat history into search, daily briefings, pending replies, commitments and opportunity tracking. Read-only via CLI and Codex skills, requires local database and authorization.
   Full card: https://gitnova.dev/en/r/Rion-Wu-tech/wechat-intelligence-hub.md
3. **evolution-foundation/evolution-go** — 0.8 · Steady · Backend & databases · Go · +0 stars today, ≈ 0 by evening
   A Go-based WhatsApp API for integrating the messenger into applications: sending messages and media, QR device pairing, events via WebSocket, webhook, RabbitMQ and NATS. Requires license activation.
   Full card: https://gitnova.dev/en/r/evolution-foundation/evolution-go.md
4. **tswawa/WechatVibe** — 1.3 · Cooling · Apps · Python · +5 stars today, ≈ 8 by evening
   Desktop client for analyzing emotions and intents in WeChat chats: recognizes intents, emotions, builds profiles of contacts and groups, scores affinity and infers MBTI. Runs locally on the Laya ONNX model or via a compatible API.
   Full card: https://gitnova.dev/en/r/tswawa/WechatVibe.md
5. **freestylefly/WeChatBridge** — 2.2 · Cooling · Productivity & self-hosted · Swift · +20 stars today, ≈ 33 by evening
   A native macOS tool that uses a Share Extension to take a WeChat chat export and forward it to AI agents (Codex, Claude, Doubao, etc.) or archive it into Obsidian. Runs fully locally without reading the WeChat database.
   Full card: https://gitnova.dev/en/r/freestylefly/WeChatBridge.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-02 14:11 UTC, updated every 30 minutes.