No install? Use cloud.anythingmcp.com directly.
Sign in, install the Insightly 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 Insightly (CRM + project management) from any AI agent: contacts, organisations, leads, opportunities, projects, tasks. 12 tools, Basic auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Insightly, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Insightly + Gemini
Drive Insightly (CRM + project management) from any AI agent: contacts, organisations, leads, opportunities, projects, tasks. 12 tools, Basic auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
INSIGHTLY_API_KEY, INSIGHTLY_POD
Paso 1 — Obtener credenciales
1 (api.insightly.com/v3.1).
Setup:
- Sign in to Insightly → bottom-left avatar → User Settings → API Key.
- Copy the key. Set
INSIGHTLY_API_KEY. - Note the API URL pod — visible in the same screen as the API key (e.g.
api.na1.insightly.comfor North America #1). SetINSIGHTLY_POD(just the pod part, e.g.na1,eu2).
Authentication: HTTP Basic with username=API_KEY, password=empty.
Pod-specific URL: https://api.{{INSIGHTLY_POD}}.insightly.com/v3.1. Wrong pod → 404.
Lead vs Contact: Insightly has both. Leads are unqualified (no opportunity yet); contacts are people in opportunities or just relationships.
…(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 —Insightlydebería 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 |
|---|---|
insightly_get_current_user | Return the user the API key belongs to (whoami) |
insightly_list_contacts | List contacts with filter/sort |
insightly_get_contact | Fetch one contact by ID |
insightly_create_contact | Create a contact |
insightly_list_organisations | List organisations (companies) |
insightly_list_leads | List leads (unqualified prospects) |
insightly_create_lead | Create a lead |
insightly_list_opportunities | List opportunities |
insightly_create_opportunity | Create an opportunity |
insightly_list_pipelines | List pipelines + their stages (FOR_OPPORTUNITIES or FOR_PROJECTS) |
insightly_list_projects | List projects |
insightly_list_tasks | List tasks (CRM activities) |
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?