Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the OpenTable 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
Search restaurants on OpenTable from any AI assistant. Find restaurants near a coordinate, read full restaurant detail (menu, hours, photos, reviews), check live table availability for a given party size and time window. 4 tools, no auth — reverse-engineered from the OpenTable mobile app.
Prueba a pedir
Prompts de ejemplo para OpenTable
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 → OpenTable, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
OpenTable + Gemini
Search restaurants on OpenTable from any AI assistant. Find restaurants near a coordinate, read full restaurant detail (menu, hours, photos, reviews), check live table availability for a given party size and time window. 4 tools, no auth — reverse-engineered from the OpenTable mobile app.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
(none — public API)
Paso 1 — Obtener credenciales
This connector wraps the OpenTable mobile app's internal API (mobile-api.opentable.co.uk).
Setup: nothing. The endpoints exposed here are the same the OpenTable iOS app uses for restaurant discovery; they do not require an API key or user login.
What it does NOT do: complete reservations. OpenTable's reservation-completion flow requires a logged-in session + payment-method-on-file + bot-detection checks that we deliberately don't automate. Use this connector to find the right restaurant and slot; book in the OpenTable app or web site.
Geo coordinate: latitude and longitude as floats. Use 48.0707,7.8674 for Freiburg, 41.3851,2.1734 for Barcelona, 40.7128,-74.0060 for NYC.
…(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 —OpenTabledebería 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 |
|---|---|
opentable_search_restaurants | Search OpenTable restaurants near a coordinate, with optional filters for party size, date/time, cuisine, and price |
opentable_get_restaurant | Full detail of one OpenTable restaurant — name, address, cuisine, hours, menu URL, photos, reviews summary, price band, dress code, parking, |
opentable_check_availability | Check live table availability at one or more OpenTable restaurants for a given party size and date/time |
opentable_autocomplete | Autocomplete restaurant or location names |
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?
