convez.ai
MCP ServerIntegração & APIsAvançado
adelaidasofia

WhatsApp MCP para Claude

adelaidasofia/whatsapp-mcp

WhatsApp seguro e auditado para Claude, com encriptação e confirmação de envio

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que integra WhatsApp ao Claude com segurança em primeiro lugar. Oferece leitura de chats, busca accent-insensitive, transcrição de notas de voz com Whisper, integração com CRM do Obsidian e confirmação obrigatória antes de enviar mensagens. Tudo roda localmente com armazenamento criptografado.

Instalação

$npx convez-ai adelaidasofia/whatsapp-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
8
Forks
11
Acompanhando
1
Saúde
57%
Último commit
há 2 dias
Versão
v0.6.0
Issues abertas
4
Contribuidores
2

Casos de uso

  • Automação de respostas e gerenciamento de chats via Claude
  • Busca inteligente em histórico de WhatsApp com tolerância a acentos
  • Transcrição local e privada de mensagens de voz
  • Integração de contexto CRM do Obsidian em conversas

Veredito

Implementação sólida e ativa de MCP WhatsApp que fecha lacunas críticas de segurança do projeto canônico desatualizado. Bom para quem precisa automação WhatsApp com garantias fortes de privacidade, auditoria e prevenção de prompt injection — mas exige setup técnico (Go, SQLCipher, Keychain).

README

A tradução para o português deste README ainda está na fila.

whatsapp-mcp

A WhatsApp MCP server for Claude, built directly on whatsmeow. Encrypted at rest, prompt-injection-scrubbed, draft-and-confirm on every send, full audit trail, daily CI security gates. Actively maintained.

Why this one?

The most-starred WhatsApp MCP (lharries/whatsapp-mcp, 5.6K stars) is the architectural reference for this pattern, but has not shipped since July 2025 and leaves the lethal-trifecta problem entirely to the user. This implementation closes the gaps:

CanonicalThis implementation
Last shippedJuly 2025Active
DB encryptionPlain SQLiteSQLCipher with key in macOS Keychain
Prompt-injection scrubberNoneEvery inbound message
Send safetyFires immediatelyMandatory confirm_send between draft and delivery
Audit logNoneEvery tool call, 30-day retention
Voice notesNot transcribedwhisper.cpp local, Spanish-tuned default
LID alias resolutionOpen issue cluster upstreamShipped, with backfill migration for legacy threads
CI securityNonegovulncheck + pip-audit + Dependabot, daily

Not a fork. The Go bridge is built directly against whatsmeow; the Python MCP layer and SQLite schema are original. Other implementations (lharries, LukasHaas, verygoodplugins) were read as reference only.

What this gives you

Claude can:

  • Read your WhatsApp chats, messages, and contacts
  • Search messages with accent-insensitive, typo-tolerant matching
  • Transcribe voice notes locally via whisper.cpp (Spanish-tuned by default)
  • Resolve LID (Linked IDentifier) names instead of numeric placeholders
  • Send text messages, reactions, and reply-quotes, with a mandatory confirm_send step between draft and delivery
  • Pull matching CRM context from your Obsidian vault when reading a chat
  • See only prompt-injection-scrubbed message text, never raw adversarial input

Everything runs locally on your machine. No cloud sync. No telemetry. Optional OpenAI Whisper backend is opt-in, off by default.

Architecture

Two components, both local:

  • whatsapp-bridge/ (Go). Binds to 127.0.0.1 only. Wraps whatsmeow for the WhatsApp Web multidevice protocol. Owns SQLite persistence with SQLCipher encryption. Handles QR and pairing-code auth, media up/download, session recovery from StreamReplaced conflicts, call history capture. Exposes a REST API the Python MCP layer consumes.
  • whatsapp-mcp-server/ (Python, FastMCP). Consumes the Go bridge REST API. Exposes 11 MCP tools to Claude: full read surface (chats, messages, contacts), accent-insensitive search, presence (typing, online, mark-read), and text-send + reactions + reply-quotes with mandatory confirm_send. Runs via uv and stdio transport.

Install

Open Claude Code, paste:

/plugin marketplace add adelaidasofia/whatsapp-mcp
/plugin install whatsapp-mcp@whatsapp-mcp

This installs the Python MCP server side. The Go bridge still needs the one-time QR pairing flow with your phone — see the legacy install block below for those steps.

See SETUP.md for step-by-step install. In short:

  1. Prereqs: Go 1.24+, Python 3.11+, FFmpeg, uv
  2. Clone this repo
  3. Run scripts/check_prerequisites.sh
  4. Start the bridge: cd whatsapp-bridge && go run .
  5. Scan the QR code with WhatsApp on your phone (Settings, Linked Devices, Link a Device)
  6. Register the MCP in your Claude Code .mcp.json
  7. Restart Claude Code

Configuration

All configurable via environment variables. See .env.example for the full list.

Key variables:

VariableDefaultPurpose
WHATSAPP_BRIDGE_PORT8080Go bridge REST API port
WHATSAPP_DB_PATH$HOME/.claude/whatsapp-mcp/store/messages.dbEncrypted SQLite database
WHATSAPP_MEDIA_PATH$HOME/.claude/whatsapp-mcp/media/Media file storage
WHATSAPP_VAULT_CRM_PATHemptyAbsolute path to your vault CRM folder for auto-injection (e.g., Obsidian 👤 CRM/). When unset, CRM injection is disabled.
WHATSAPP_WHISPER_BACKENDlocal-cpplocal-cpp (private) or openai-api (opt-in)
WHATSAPP_WHISPER_API_KEYemptyRequired only when backend is openai-api
WHATSAPP_WHISPER_MODELlarge-v3whisper.cpp model name
WHATSAPP_SCRUB_PROMPT_INJECTIONtrueStrip known prompt-injection patterns from incoming messages before Claude sees them
WHATSAPP_AUDIT_LOGtrueLog every tool call to audit.log
WHATSAPP_ENCRYPT_DBtrueEnable SQLCipher DB encryption with key from macOS Keychain

Security

This MCP is the highest-trust component in your Claude stack because every WhatsApp message you receive flows through it. See SECURITY.md for the threat model, tool risk-tier classification, and the full list of hardening decisions.

Short version:

  • Bridge binds to 127.0.0.1 only, never 0.0.0.0
  • SQLite encrypted at rest with SQLCipher; key stored in macOS Keychain
  • Every tool call logged to audit.log with 30-day retention
  • Send tools require an explicit confirm_send step between draft and delivery
  • Incoming message text passes through a prompt-injection scrubber before Claude sees it
  • whatsmeow pinned to a specific commit; upgrades require diff review
  • No telemetry, no external API calls by default

Status

v0.1.0, actively maintained.

Shipped: QR + pairing-code auth, full read surface (chats, messages, contacts), accent-insensitive NFD-normalized search, LID alias resolution with backfill migration for legacy threads, Baileys-store import for one-shot history migration, vault-format markdown export, local whisper.cpp voice transcription, presence (typing, online, mark-read), text-send with mandatory confirm_send, reactions, reply-quotes, prompt-injection scrubber, SQLCipher-encrypted persistence with macOS Keychain key handling, audit log, CI security gates.

Not yet shipped: media-send (image, document), audio-message-send (FFmpeg-Opus path), group broadcast helpers.

See CHANGELOG.md for full history.

MCP Registry

Published on the official MCP Registry under io.github.adelaidasofia/whatsapp-mcp. Two live channels:

  • .mcpb bundle (canonical, recommended) — one-click install in Claude Desktop / Cursor / any MCPB-aware client. Published as a GitHub release artifact at releases/latest/download/whatsapp-mcp.mcpb. The release manifest carries the SHA256 for tamper detection.
  • PyPI package (adelaidasofia-whatsapp-mcp) — historical; available via uvx adelaidasofia-whatsapp-mcp for stdio-installer flows. The unprefixed names (whatsapp-mcp, whatsapp-mcp-server) are taken by unrelated projects on PyPI, hence the username-prefixed namespace.

The verification marker mcp-name: io.github.adelaidasofia/whatsapp-mcp is embedded in this README (HTML comment near the top) so the registry can verify package-to-server ownership at publish time.

Publishing pipeline: built and shipped via the Mycelium MCP publishing pipeline (two-phase: .mcpb bundle build, then gh release + mcp-publisher publish). The same pipeline produced all 16 sibling MCPs in this family.

Related MCPs

Same author, same architecture pattern (FastMCP, draft+confirm on writes where applicable, vault auto-export, MIT):

Telemetry

This plugin sends a single anonymous install signal to myceliumai.co the first time it loads in a Claude Code session on a given machine.

What is sent:

  • Plugin name (e.g. slack-mcp)
  • Plugin version (e.g. 0.1.0)

What is NOT sent:

  • No user identifiers, names, emails, tokens, or API keys
  • No file paths, message content, or anything from your work
  • No IP address is stored after dedup processing

Why: Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.

Opt out: Set the environment variable MYCELIUM_NO_PING=1 before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at ~/.mycelium/onboarded-<plugin> — delete it if you want to reset state.

License

MIT. See LICENSE.

Not affiliated with WhatsApp or Meta

WhatsApp is a trademark of Meta Platforms, Inc. This project is an independent open-source tool that uses WhatsApp's public web-multidevice protocol. Use of this tool may violate WhatsApp's Terms of Service. Use at your own risk. The authors provide no warranty and accept no liability for account suspension, data loss, or other consequences.


Built by Mycelium AI. MIT license.

Ver o original no GitHub

Bom para

Relacionados