WhatsApp MCP Server

MCPOpen SourceMIT87.9

by lharries • Messaging & Collaboration

A personal WhatsApp Model Context Protocol (MCP) server that lets agents search, read, and send WhatsApp messages and media via a local bridge and SQLite store.

Example Use Cases

1
Search and read a user's personal WhatsApp message history (including images, videos, documents, and audio) stored locally in SQLite.
2
Send messages or media (images, videos, documents, and voice messages) to individual contacts or groups via the WhatsApp web multidevice bridge.
3
Download and convert media (including converting audio to .ogg/Opus with ffmpeg) and retrieve message context or surrounding messages for better responses.

Description

This project connects a personal WhatsApp account through a Go WhatsApp bridge (whatsmeow) and exposes the data and actions via a Python MCP server. All messages and media metadata are stored locally in SQLite, and the MCP tools let an LLM (e.g., Claude) search messages, list chats, download media, and send text or media messages. It supports sending voice messages (with optional ffmpeg-based conversion to .ogg/Opus) and integrates with Claude Desktop or Cursor as an MCP integration. The design keeps data local and only shares message content with an LLM when the agent invokes the provided tools.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D49/100

5/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerlharries

CategoryMessaging & Collaboration

DependenciesStandalone