List WhatsApp Chats with AI on Mac

The whatsapp_list_chats tool lets your AI assistant read the list of WhatsApp conversations open on your Mac. It returns each chat's ID, the contact or group name, and a short preview of the most recent message — so the AI can see who you've been talking to and what was last said, without you opening WhatsApp yourself. A typical prompt looks like: "List my recent WhatsApp chats and tell me which ones I haven't replied to yet."

Because the AI gets real chat IDs and names back, it can reason about your actual conversations instead of guessing. Ask it "Which WhatsApp threads mention dinner this week?" or "Show me my last 10 WhatsApp chats with a one-line summary of each." and it answers from your live data. Download LMCP to get started.

Which AI agents work?

LMCP exposes whatsapp_list_chats to every major MCP-capable assistant:

• Desktop clients — Claude Desktop, Cursor, VS Code (GitHub Copilot), Windsurf and Zed auto-configure through a local stdio connection. No keys to paste.
• Web AIs — ChatGPT, Claude.ai (web), Grok and Perplexity connect through the LMCP Cloud Relay connector, which securely bridges the web assistant to your Mac.

The same tool, and the full set of 150+ tools, is available to all of them.

Automation

whatsapp_list_chats is the entry point for almost any WhatsApp workflow. The AI calls it first to discover chat IDs, then chains into other tools: read the full thread of a specific chat, draft a reply, or pull a contact's details from Contacts. For example: "List my WhatsApp chats, find the one with my plumber, read the last messages, and draft a confirmation reply." The AI walks the chain — list, read, compose — in a single instruction. It can also cross WhatsApp data with your Calendar or Reminders, turning a chat preview into a scheduled follow-up.

Context

This tool works against the WhatsApp data already on your Mac — your real conversations, real contact names, real recent messages. The AI isn't working with a sandbox or sample data; it sees the same chat list you do. That means answers are grounded in what's actually happening in your inbox right now, so summaries, triage and follow-ups reflect your true backlog instead of a generic guess.

Productivity

Scanning WhatsApp manually to figure out who's waiting on you eats minutes every hour. With whatsapp_list_chats, one prompt surfaces your whole conversation list with previews, and the AI can immediately flag unanswered threads, group them by topic, or prioritize them. Instead of switching apps and scrolling, you ask once and get a ranked, summarized view. Over a day of context-switching, that's real time saved — and fewer dropped conversations.

Privacy & GDPR

Everything runs locally on your Mac. whatsapp_list_chats reads your WhatsApp data on-device and hands it straight to your AI client — nothing is uploaded to an LMCP server, nothing is stored in the cloud, and there are no API keys to manage. Your conversations never leave your machine. This local-only design makes LMCP GDPR-compliant by architecture: there's no third-party data processor to audit because there's no third party in the loop.