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.
Prova a chiedere
Prompt di esempio per Crisp
Clicca su un prompt per copiarlo. Incollalo in Claude, ChatGPT, Cursor, Gemini, Copilot o OpenClaw per eseguirlo contro questo connettore.
Claude è un'AI e può sbagliare. Verifica sempre le risposte.
💡 Niente installazione? Vai direttamente su cloud.anythingmcp.com. Accedi, clicca Connectors → Crisp, inserisci le credenziali, genera una MCP API key — fatto. Niente Docker, niente
git clone, niente server locale.
Crisp + Gemini
Drive Crisp (live chat + helpdesk) from any AI agent: conversations, messages, people, tickets. 11 tools, plugin-token Basic auth + tier header.
Prerequisiti
Le istruzioni di setup complete sono incluse nel connettore stesso (visibili nello store quando lo selezioni). Le variabili d'ambiente richieste sono:
CRISP_PLUGIN_IDENTIFIER, CRISP_PLUGIN_KEY, CRISP_WEBSITE_ID
Step 1 — Ottieni le credenziali
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)
Step 2 — Installa l'adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Step 3 — Aggiungi il connettore in Gemini
Gemini CLI legge i server MCP da ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json su Windows). Aggiungi:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Ottieni la tua MCP API key da AnythingMCP → Profilo → MCP API Keys → Nuova Key.
- Salva il file e riavvia
gemini. - Esegui
/mcpnella Gemini CLI —Crispdovrebbe essere elencato come disponibile. - Vertex AI Studio: passa
https://cloud.anythingmcp.com/mcpnell'arraytoolsdella richiesta con lo stesso header Bearer.
Tool disponibili
| 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 supportano MCP? Sì — Gemini CLI ≥ 0.4 e la Vertex AI tools API accettano connettori MCP httpUrl con header Bearer.
Prossimi passi
Questa guida ti è stata utile?
