Sáltate la instalación. Funcionando en menos de 2 minutos.
Inicia una prueba gratuita en cloud.anythingmcp.com, añade EspoCRM con un clic y apunta tu cliente de IA (Claude, ChatGPT, Copilot o Cursor) al endpoint MCP generado. Sin Docker, sin git clone, sin experiencia de desarrollo.
Summary
EspoCRM open-source CRM: accounts, contacts, leads, opportunities, cases, calls, meetings and tasks, plus a generic entity route for custom entities. API-key auth against your own instance.
Prueba a pedir
Prompts de ejemplo para EspoCRM
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 → EspoCRM, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
EspoCRM + Gemini
EspoCRM open-source CRM: accounts, contacts, leads, opportunities, cases, calls, meetings and tasks, plus a generic entity route for custom entities. API-key auth against your own instance.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
ESPOCRM_URL, ESPOCRM_API_KEY
Paso 1 — Obtener credenciales
Getting a key
- In EspoCRM go to Administration → API Users and create an API user. Choose API Key authentication (not HMAC — this adapter sends the plain key).
- Assign a role that grants read access to the entities the agent should see. EspoCRM enforces roles per entity and per field, so a restricted role produces fewer rows and fewer columns rather than an error.
- Copy the generated key into
ESPOCRM_API_KEYand setESPOCRM_URLto your instance root (no trailing slash, no/api/v1).
The header is X-Api-Key.
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
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 —EspoCRMdebería 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 |
|---|---|
espocrm_get_app_user | Read the API user this key belongs to, with their roles and the entity permissions they carry |
espocrm_list_entities | List records of any entity type with a single where clause |
espocrm_get_entity | Read one record of any entity type by id, with every attribute the API user's role permits |
espocrm_list_accounts | List accounts — the customer companies — with their name, industry, website, phone, billing city and assigned user |
espocrm_list_contacts | List contacts with their name, account, e-mail, phone and title, to find the person before logging an interaction against them |
espocrm_list_opportunities | List opportunities with their name, account, amount, stage, probability and close date — the sales-pipeline view |
espocrm_list_leads | List leads with their name, company, status, source, e-mail and phone — the top of the funnel, before conversion into an account |
espocrm_list_cases | List support cases with their number, subject, status, priority, account and assigned user |
espocrm_get_related | List the records linked to one record — the contacts on an account, the opportunities on a contact, the activities on anything |
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?
