No install? Use cloud.anythingmcp.com directly.
Sign in, install the Help Scout in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Help Scout (shared inbox + helpdesk) from any AI agent: conversations, customers, mailboxes, tags, threads. 13 tools, OAuth2 Bearer auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Help Scout, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Help Scout + Gemini
Drive Help Scout (shared inbox + helpdesk) from any AI agent: conversations, customers, mailboxes, tags, threads. 13 tools, OAuth2 Bearer auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
HELPSCOUT_ACCESS_TOKEN
Paso 1 — Obtener credenciales
helpscout.com/mailbox-api).
Setup:
- Sign in to Help Scout → Manage → Apps → My Apps → Create My App.
- Pick app type:
- Personal Access Token (single-user): get a token from your profile → API Keys → Personal Access Token. Token expires after 2 days — refresh needed.
- OAuth2 App (multi-user / longer-lived): standard OAuth2 client-credentials or auth-code flow.
- Set
HELPSCOUT_ACCESS_TOKENto the access token.
Authentication: Authorization: Bearer ${HELPSCOUT_ACCESS_TOKEN}. Tokens expire — your orchestrator handles refresh.
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —Help Scoutdebería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
help_scout_list_mailboxes | List mailboxes (shared inboxes) |
help_scout_list_conversations | List conversations with filters |
help_scout_get_conversation | Fetch a single conversation with full details |
help_scout_create_conversation | Create a new conversation (ticket) |
help_scout_update_conversation_status | Change conversation status (close, reopen, snooze) |
help_scout_add_reply | Add a public reply (emails the customer) to a conversation |
help_scout_add_note | Add an internal note (not visible to customer) |
help_scout_list_conversation_threads | List all threads (replies, notes, status changes) in a conversation |
help_scout_list_customers | List customers (people the business interacts with) |
help_scout_get_customer | Fetch a customer's full profile including emails[], phones[], chats[], social_profiles[], address |
help_scout_create_customer | Create a customer |
help_scout_list_tags | List tags on the account |
help_scout_list_users | List Help Scout agents |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?