WhatsApp Web MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_TOKEN | No | Token opcional para diarização | |
| FFMPEG_BIN | No | Executável FFmpeg | |
| WHISPERX_PYTHON | No | Python que possui WhisperX | |
| WHISPERX_MODEL_DIR | No | Cache/modelos WhisperX | |
| WHATSAPP_MCP_DATA_DIR | No | Raiz de dados, estado e exports | |
| WHATSAPP_MCP_STATE_DIR | No | Override apenas do estado | |
| WHATSAPP_MCP_OUTPUT_DIR | No | Override apenas dos exports | |
| WHATSAPP_MCP_BROWSER_BIN | No | Chrome/Chromium específico |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| whatsapp_capabilitiesA | Mostra caminhos, formatos e backends suportados por este MCP. |
| whatsapp_browser_policyC | Resolve politica headless/headed para uma operacao sem persistir overrides. |
| whatsapp_set_browser_policyC | Persiste default headless/headed global, por categoria, ou por processo dentro da categoria. |
| whatsapp_browser_runtime_statusA | Mostra disponibilidade de Playwright/Chrome e sessoes de browser abertas. |
| whatsapp_browser_openC | Abre WhatsApp Web via Playwright em modo headless/headed e retorna screenshot/QR quando solicitado. |
| whatsapp_browser_closeC | Fecha uma sessao Playwright aberta pelo MCP. |
| whatsapp_sourcesC | Mostra fontes disponiveis. Apenas WhatsApp Web e anunciado. |
| whatsapp_automated_search_planC | Planeja busca automatizada por DOM/acessibilidade em WhatsApp Web. |
| whatsapp_find_contactsD | Lista ou procura contatos/chats pelo WhatsApp Web DOM, sem SQLite. |
| whatsapp_select_contextC | Seleciona contato/conversa pelo WhatsApp Web DOM. |
| whatsapp_search_messagesC | Busca mensagens renderizadas no WhatsApp Web por contato, texto, tipo e intervalo. |
| whatsapp_chat_structureC | Mostra estrutura do chat por dia/hora usando mensagens renderizadas no WhatsApp Web. |
| whatsapp_export_conversationC | Exporta conversa renderizada do WhatsApp Web para JSON, com midia/transcricao quando possivel. |
| whatsapp_prepare_send_messageB | Prepara envio de texto/midia, mas nao envia. Retorna token que exige confirmacao explicita. |
| whatsapp_confirm_send_messageC | Confirma uma mensagem preparada. Nao despacha sem backend Web/UI verificado. |
| whatsapp_probe_send_mediaB | Anexa uma midia ate o preview e fecha sem enviar. Usado para validar Web UI por tipo. |
| whatsapp_probe_reply_to_messageC | Entra no modo resposta nativo do WhatsApp Web e cancela sem enviar. |
| whatsapp_transcribe_fileC | Transcreve arquivo manualmente com WhisperX, incluindo video via audio extraido. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 18 tools
Each tool has a distinct purpose, from browser management to message preparation and confirmation. The 'probe' tools simulate actions without sending, clearly differentiating from actual send operations. There is no ambiguity between tools.
All tools share the 'whatsapp_' prefix, and most follow a verb_noun pattern (e.g., export_conversation, find_contacts). A few tools use noun phrases (e.g., whatsapp_automated_search_plan, whatsapp_capabilities) but the overall pattern is predictable and readable.
With 18 tools, the server covers a broad but scoped domain of WhatsApp Web automation. Each tool has a clear role, from browser lifecycle to message handling and media probing. The number is reasonable and not excessive.
The tool set covers core workflows: browser control, contact/chat selection, message sending (with prepare and confirm), search, structure, and media transcription. Minor gaps like direct read without search are acceptable given the automated interaction focus.