Give Muse
a little See Food.

Name a restaurant. Your agent follows the See Food method to explore its real menu, with your tastes in mind.

Open Muse

Loading the prompt…

Read or copy the prompt manually

Start in your conversation.

  1. Copy the prompt and paste it into Muse.
    It includes this site’s address and the agent reading entry.
  2. Name the restaurant and branch.
    Or send a photo of the menu. Muse uses preferences it already knows, and only asks for details that change the recommendations.
  3. Explore the menu Muse creates.
    The original dishes stay in order. Photos, sources, stories and suggestions help you choose.

No See Food account or profile upload. This starts the method in the conversation; it does not claim a verified connector installation or permanent memory.

Ask for what matters to you.

“We’re going to Piatti Danville for dinner. Use See Food to help us explore the menu. We’d like a few dishes to share, and non-alcoholic pairings.”

Start with a quick look, or ask for deeper research. Muse handles browsing, generation and any supported saving or sharing.

What about a reusable connector?

Muse can use these public workflow files directly. A local MCP adapter is also provided for development. A public MCP endpoint and an actual Muse connection still require deployment and verification.

Read the agent integration guide

Connect See Food.

The public API requires no key or OAuth. Give Muse the OpenAPI document and installation instructions to create a custom connector. Public API calls work directly. Muse requires authentication. OAuth server configuration is ready; Muse REST and MCP connections were verified with the owner account; Google login is available to external users.