Skip to main content
Glama
Sign In
WACrew

WACrew

by sumioshi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to WACrew

  • wa-mcp

    girik7
    A
    license
    Not graded
    quality
    C
    maintenance
    Self-hosted WhatsApp management over Model Context Protocol, exposing a streamable HTTP MCP endpoint with 30 tools for session/QR pairing, messaging, media storage, and optional on-CPU voice note transcription via whisper.cpp.
    MIT

  • whatsapp-mcp-plus

    eeshsaxena
    A
    license
    Not graded
    quality
    C
    maintenance
    A secure, zero-setup WhatsApp MCP server that lets AI assistants read, search, summarize, and (with user confirmation) act on personal WhatsApp chats via a safety-focused toolset, built as a maintained successor to the abandoned whatsapp-mcp.
    5
    MIT

Related Servers

  • OpenWA MCP Server

    LoopyOratory
    F
    license
    Not graded
    quality
    D
    maintenance
    OpenWA MCP server that bridges AI agents to the OpenWA WhatsApp API, exposing 40 tools for sessions, messages, contacts, groups, and webhooks so agents can read and send WhatsApp messages through a self-hosted OpenWA gateway.
    -

  • WhatsApp Channel

    diegomichel19
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables driving a Claude Code (or other MCP client) session directly from WhatsApp chats, with bidirectional messaging, media and locally transcribed voice notes, polls, per-group personalities, cron tasks, and emoji-reaction approval of tool requests. Inbound traffic is gated by pairing codes, allowlists, and per-group policies, and it runs either through a linked personal-device account or Meta's official Cloud API for business DMs.
    MIT

  • whatsapp

    cRodriguez83407
    A
    license
    Not graded
    quality
    A
    maintenance
    A stdio MCP server that lets Claude Code sessions be driven directly from WhatsApp chats, with bidirectional messaging and media, voice-note transcription, pairing-code access control, per-group personalities, and emoji-reaction approval of tool requests. It supports both linked-device pairing for personal numbers and the official WhatsApp Cloud API for business DMs, and can also be run by other MCP clients on a poll-based basis.
    MIT

  • WhatsApp Desktop MCP

    srijonbasak
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that connects WhatsApp Web to AI tools like Gemini and Claude, providing chat reading, messaging, and a local CRM with draft-and-approve workflows.
    MIT

  • wa-bridge

    xbirimensah
    A
    license
    Not graded
    quality
    C
    maintenance
    A self-hosted WhatsApp bridge that exposes a stdio MCP server with ~20 tools for reading conversations, sending messages, managing groups, contacts, and aliases, enabling AI agents to operate WhatsApp directly.
    4
    MIT

  • Relay

    viaanshetty3-debug
    A
    license
    Not graded
    quality
    B
    maintenance
    Links your own WhatsApp account as a linked device on a computer you control and exposes it to Claude and ChatGPT over MCP, so assistants can search and read chat history, analyze attachments such as voice notes and PDFs, and send or manage messages only when explicitly asked. It runs self-hosted on macOS, Linux or Windows with an optional encrypted Cloudflare relay and a standby bridge for automatic, no-duplicate failover.
    MIT
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 36 tools

Disambiguation3/5

Most tools target genuinely different actions, and the descriptions work hard to separate them (e.g. caixa_de_entrada vs novidades vs ler_mensagens). But several near-pairs remain easy to mix up: ver_video vs assistir_video, preparar_resposta vs revisar_texto, and the four read-the-chat tools all overlap enough that an agent must read long descriptions to choose correctly.

Naming Consistency3/5

Naming is uniformly Portuguese and mostly infinitive verbs, but the structure varies: verb_noun (ler_mensagens, listar_grupos), object_prefix (agenda_ver, agenda_marcar, agenda_editar, agenda_apagar), bare verbs (responder, buscar, anotar, reagir, etiquetar), and bare nouns (dashboard, novidades, caixa_de_entrada, estado_triagem, resumo_do_dia). Readable, but no single predictable pattern.

Tool Count2/5

36 tools is heavy for a single server, well past the comfortable 3-15 range. Most tools do earn their place in a rich domain (messaging, media, calendar, CRM, dashboard), but the surface is large enough that discovery and selection cost is significant.

Completeness4/5

The surface covers read/send/edit/react/media/transcription plus triage state, notes, contracts, features, delivery status, and a clean calendar CRUD cycle. Gaps are minor and workable around: no group administration (create group, add/remove participants), no poll/sticker sending, no contact creation.

Maintenance

ActivityActive
ResponsivenessNo recent community issues

Resources