No install? Use cloud.anythingmcp.com directly.
Sign in, install the Nutshell CRM in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Manage Nutshell CRM (leads, contacts, accounts, activities, tasks) from any AI agent. 9 tools, basic-auth with API token.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Nutshell CRM klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Nutshell CRM + Gemini
Manage Nutshell CRM (leads, contacts, accounts, activities, tasks) from any AI agent. 9 tools, basic-auth with API token.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
NUTSHELL_USERNAME, NUTSHELL_API_KEY
Schritt 1 — Zugangsdaten holen
This connector wraps the Nutshell REST API v1 (app.nutshell.com/api/v1).
Setup:
- Log into https://app.nutshell.com → top-right avatar → Setup → API → New API key.
- Note the
Username(your Nutshell email) and the generatedAPI key. - Set
NUTSHELL_USERNAME(email) andNUTSHELL_API_KEY.
Authentication: HTTP Basic — username = your account email, password = the API key. Nutshell ALSO supports a legacy JSON-RPC API but the REST endpoints exposed here are easier to consume.
Entity types: Lead (the main pipeline opportunity), Contact (person), Account (company), Activity (call/meeting log), Task (todo). Each has its own endpoint root.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —Nutshell CRMsollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| Tool | What it does |
|---|---|
nutshell_list_leads | List leads |
nutshell_get_lead | Get one lead by ID with full custom fields, products, activities |
nutshell_create_lead | Create a lead |
nutshell_list_contacts | List contacts |
nutshell_create_contact | Create a contact |
nutshell_list_accounts | List accounts (companies) |
nutshell_create_account | Create a company |
nutshell_list_activities | List activities (calls, meetings, emails, log notes) |
nutshell_create_task | Create a task assigned to a user, optionally linked to a lead/contact/account |
FAQ
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?