Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Crisp in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Drive Crisp (live chat + helpdesk) from any AI agent: conversations, messages, people, tickets. 11 tools, plugin-token Basic auth + tier header.
Prueba a pedir
Prompts de ejemplo para Crisp
Haz clic en un prompt para copiarlo. Pégalo en Claude, ChatGPT, Cursor, Gemini, Copilot u OpenClaw para ejecutarlo contra este conector.
Claude es IA y puede equivocarse. Verifica siempre las respuestas.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Crisp, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Crisp + Gemini
Drive Crisp (live chat + helpdesk) from any AI agent: conversations, messages, people, tickets. 11 tools, plugin-token Basic auth + tier header.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
CRISP_PLUGIN_IDENTIFIER, CRISP_PLUGIN_KEY, CRISP_WEBSITE_ID
Paso 1 — Obtener credenciales
crisp.chat/api/v1/).
Setup:
- Sign in to Crisp → Marketplace → Create a Plugin (the modern way for API access; the legacy User token approach is deprecated).
- Pick scopes: at minimum
website:conversation:read,website:conversation:write,website:people:read. - After creating + reviewing, you get
plugin_id,plugin_identifier,plugin_key(the credentials). - Install the plugin on your website (give it a website_id to act on).
- Set:
CRISP_PLUGIN_IDENTIFIER= the identifierCRISP_PLUGIN_KEY= the keyCRISP_WEBSITE_ID= the website ID to operate on
…(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 —Crispdebería 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 |
|---|---|
crisp_get_website | Get website info (name, domain, logo) |
crisp_list_conversations | List conversations with filters |
crisp_get_conversation | Fetch a conversation by session_id with metadata + state |
crisp_list_messages | List messages in a conversation |
crisp_send_message | Send a message in a conversation as the operator |
crisp_update_conversation_state | Change conversation state: pending, unresolved, resolved |
crisp_assign_conversation_routing | Assign a conversation to an operator |
crisp_list_people_profiles | List people (contact profiles) across the website |
crisp_get_people_profile | Fetch a people profile by people_id (UUID) or email/phone (URL-encoded) |
crisp_update_people_profile | Update a people profile (segments, attributes, notes) |
crisp_list_operators | List operators (agents) on the website |
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?
