No install? Use cloud.anythingmcp.com directly.
Sign in, install the Front 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 Front (collaborative inbox) from any AI agent: conversations, messages, contacts, tags, inboxes, teammates. 13 tools, API-key Bearer auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Front, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Front + Gemini
Drive Front (collaborative inbox) from any AI agent: conversations, messages, contacts, tags, inboxes, teammates. 13 tools, API-key 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:
FRONT_API_TOKEN
Paso 1 — Obtener credenciales
frontapp.com/reference).
Setup:
- Sign in to Front → Settings (top-right) → Developers → API Tokens → Create API Token.
- Pick scope:
private(full-access to all inboxes/conversations) or scoped to a specific inbox/role. - Copy the token. Set
FRONT_API_TOKEN.
Authentication: Authorization: Bearer ${FRONT_API_TOKEN}.
Front's tile model:
- Conversation = a thread between your team and one or more contacts. Has status (open/archived/spam/deleted), assignee, inbox, tags.
- Message = each inbound/outbound email, SMS, chat, etc. within a conversation.
- Contact = an external entity (a customer). …
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 —Frontdebería 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 |
|---|---|
front_me | Return the API token's identity (id, name, email) |
front_list_inboxes | List inboxes the token can access |
front_list_conversations | List conversations with optional filtering |
front_get_conversation | Fetch a single conversation including assignee, tags, recipient handles, links to messages/comments |
front_list_conversation_messages | List all messages in a conversation chronologically |
front_send_reply | Send a reply (new message) in an existing conversation |
front_add_comment | Add an internal comment (private note) to a conversation |
front_update_conversation | Update conversation status, assignee, or tags |
front_list_contacts | List contacts (external entities) |
front_get_contact | Fetch a contact with all handles[] (email/phone/twitter/custom) |
front_create_contact | Create a contact |
front_list_tags | List tags |
front_list_teammates | List teammates (Front users) |
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?