No install? Use cloud.anythingmcp.com directly.
Sign in, install the Streak 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 Streak (CRM inside Gmail) pipelines, boxes, contacts, fields from any AI agent. 9 tools, basic-auth with API key.
💡 Niente installazione? Vai direttamente su cloud.anythingmcp.com. Accedi, clicca Connectors → Streak, inserisci le credenziali, genera una MCP API key — fatto. Niente Docker, niente
git clone, niente server locale.
Streak + Gemini
Manage Streak (CRM inside Gmail) pipelines, boxes, contacts, fields from any AI agent. 9 tools, basic-auth with API key.
Prerequisiti
Le istruzioni di setup complete sono incluse nel connettore stesso (visibili nello store quando lo selezioni). Le variabili d'ambiente richieste sono:
STREAK_API_KEY
Step 1 — Ottieni le credenziali
This connector wraps the Streak REST API v1/v2 (api.streak.com/api).
Setup:
- Sign in to https://www.streak.com → top-right gear → Settings → API keys → Generate API key.
- Copy the key. Set
STREAK_API_KEY.
Authentication: HTTP Basic — API key is the username, password is empty:
Authorization: Basic base64(API_KEY:)
Streak vocabulary:
- Pipeline = a CRM workflow (e.g. 'Sales', 'Hiring').
- Box = a record/deal/case inside a pipeline.
- Stage = pipeline column (e.g. 'Lead', 'Qualified', 'Closed Won').
- Field = custom field on a pipeline (definition) or box (value).
…(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 —Streakdovrebbe 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 |
|---|---|
streak_current_user | Returns the authenticated user: userKey, displayName, email, isOauth, lastSeenTimestamp |
streak_list_pipelines | List all pipelines the user has access to |
streak_get_pipeline | Get one pipeline with stages and field definitions |
streak_list_boxes | List boxes (records) in a pipeline |
streak_get_box | Get one box with full custom-field values, assigned users, linked contacts, and Gmail thread refs |
streak_create_box | Create a new box in a pipeline |
streak_update_box | Update a box: rename, move stage, set custom field values |
streak_list_box_notes | List notes attached to a box |
streak_add_box_note | Add a text note to a box |
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?