Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Folk 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 Folk (modern relationship CRM) from any AI agent: people, companies, groups, deals, custom fields. 9 tools, Bearer auth.
Prueba a pedir
Prompts de ejemplo para Folk
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 → Folk, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Folk + Gemini
Drive Folk (modern relationship CRM) from any AI agent: people, companies, groups, deals, custom fields. 9 tools, Bearer auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
FOLK_API_TOKEN
Paso 1 — Obtener credenciales
folk.app).
Setup:
- Sign in to https://app.folk.app → bottom-left avatar → API & Integrations → API → Generate API token.
- Set
FOLK_API_TOKEN. - Note your workspace's groups — Folk's groups are loose collections (use them like tags).
Authentication: Authorization: Bearer ${FOLK_API_TOKEN}.
People / Companies / Deals: standard CRM objects, plus the relationship-graph idea — every person is linked to one or more companies, plus a free-form network of contacts.
Groups: flexible — Folk's primary segmentation. Add a person to multiple groups; each group has its own custom fields visible only when the person is in that group.
…(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 —Folkdebería 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 |
|---|---|
folk_me | Return the user the token belongs to |
folk_list_people | List people with cursor pagination |
folk_get_person | Fetch a person by ID with full contact details + groups + companies |
folk_create_person | Create a person |
folk_update_person | Update a person (PATCH) |
folk_list_companies | List companies |
folk_create_company | Create a company |
folk_list_groups | List groups (collections) |
folk_list_group_custom_fields | List custom fields defined on a specific group |
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?
