Hi HN – I built an open-source, self-hosted Model Context Protocol (MCP) server for WhatsApp: https://github.com/lharries/whatsapp-mcp
It connects to your personal WhatsApp account via the WhatsApp Web multi-device API (using whatsmeow from the Beeper team), and doesn't rely on third-party APIs. All messages are stored locally in SQLite. Nothing is sent to the cloud unless you explicitly allow your LLM to access the data via tools – so you maintain full control and privacy.
The MCP server can:
- Search your messages, contacts, and groups
- Send WhatsApp messages to individuals or groups
Why build this?
99% of your life is stored in WhatsApp, by connecting an LLM to WhatsApp you get all this context. And your AI agent can execute tasks on your behalf by sending messages.
Comments URL: https://news.ycombinator.com/item?id=43532967
Points: 22
# Comments: 2
Login to add comment
Other posts in this group

Get it from here: https://github.com/c3lang/c3c
In 2019, while contributing to the C2 language, I started up "C3" as a pet project whil

Benchi is a CLI tool for running benchmarks and collecting metrics. It's using Docker Compose to orchestrate the infrastructure and tools being benchmarked, making it repeatable and runnable on di
I've been a long-time Cloudflare user, but sometimes I just want a global load balancer without the lock-in and with full configuration control (e.g., some Cloudflare rules require an enterprise p

Article URL: https://ai-2027.com/
Comments URL: https://news.ycombinator.com/item?id=43571851
They've pulled their browser extensions and integrations except for Firefox. The definition of blatant enshitification and anti-competitive. Moz needs to be held accountable by the EU for this kin
