Self-hosted WhatsApp MCP server: connect your personal WhatsApp number to Claude, ChatGPT or any LLM, with a web UI and configurable auto-reply.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"personal-whatsapp-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# personal-whatsapp-mcp — WhatsApp MCP server for Claude and any LLM [](https://github.com/Gnaneshdivi/personal-whatsapp-mcp/actions/workflows/ci.yml) [](https://www.python.org/downloads/) [](LICENSE) [](https://modelcontextprotocol.io) **Connect your personal WhatsApp number to Claude, ChatGPT, or any Model Context Protocol client — and reply automatically when you are away.** Self-hosted, open source, and a single process. One phone number, 23 MCP tools, a web UI that looks like WhatsApp Web, and an auto-reply you configure rather than code. No Redis, no database server, no build step. SQLite is the default and ships with Python. > **This project is independent and is not affiliated with WhatsApp or Meta.** > It links to your account the same way WhatsApp Web does, through > [whatsmeow](https://github.com/tulir/whatsmeow). Use it at your own risk: > WhatsApp's Terms of Service govern what you may do with your account, and > automating replies to real people is your responsibility, not this > project's. ## Contents - [Install](#install) - [What it is](#what-it-is) - [What it is not](#what-it-is-not) - [MCP tools](#mcp-tools) - [Setup and installation](#setup-and-installation) - [What you need](#what-you-need) - [Install](#install-1) - [First run](#first-run) - [Connecting an AI client](#connecting-an-ai-client) - [Running it beyond this machine](#running-it-beyond-this-machine) - [Configuration](#configuration) - [Storage](#storage) - [Upgrading](#upgrading) - [Command line](#command-line) - [Logging out](#logging-out) - [Auto-reply](#auto-reply) - [What this is not](#what-this-is-not) - [Two modes](#two-modes) - [The prompt](#the-prompt) - [When it does …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.