No install? Use cloud.anythingmcp.com directly.
Sign in, install the Fillout in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Read Fillout (modern form/survey builder) form definitions and submissions from any AI agent. 6 tools, Bearer auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → Fillout, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
Fillout + Gemini
Read Fillout (modern form/survey builder) form definitions and submissions from any AI agent. 6 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:
FILLOUT_API_KEY
Paso 1 — Obtener credenciales
com/help/developers).
Setup:
- Sign in to https://fillout.com → top-right avatar → Settings → Developer → API → Create API key.
- Set
FILLOUT_API_KEY.
Authentication: Authorization: Bearer ${FILLOUT_API_KEY}.
Form IDs: each form has a 32-character ID (visible in form URL). Use fillout_list_forms to discover.
Submission shape: each submission has questions[] array of {id, name, type, value}. Cross-reference with form questions for human-readable names.
Pagination: ?limit=N&offset=M. Submissions endpoint supports ?afterDate=ISO&beforeDate=ISO.
Out of scope here: form creation (UI), file uploads, webhook subscription management.
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 —Filloutdebería 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 |
|---|---|
fillout_list_forms | List forms in the workspace |
fillout_get_form | Fetch a form's full definition: questions[] (id, name, type, options), settings |
fillout_list_submissions | List submissions for a form, with optional date range filter |
fillout_get_submission | Fetch one submission with full answers |
fillout_delete_submissions | Delete one or more submissions by ID |
fillout_create_submission | Programmatically create a submission |
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?