
Seemor
ClaudecommunityWhere to eat, graded from what reviews actually say
Larracos Labs, Ltd.
Seemor reads what people actually wrote in restaurant reviews and menus, then grades each restaurant and explains the grade in plain words: what to order, how loud it is, whether it suits a date, a family or a group, and what people complain about. Ask Claude things like "a quiet Italian for a date night in Soho", "where should six of us eat near Shibuya station", "is Barrafina worth it", or "what should I order at Dishoom". Seemor returns a short, ranked answer with a grade for each place, the reasons it fits your ask, and anything it misses. It says plainly when it has not analysed a place or when coverage in an area is thin. Coverage: more than 70 countries, over 2 million restaurants catalogued, more than a quarter of a million analysed and graded (September 2026). Deepest in major cities across Europe, North America, the Middle East and Asia. Connecting creates a free Seemor account with your email. Connected accounts get 10 recommendations and 15 restaurant questions a day; searching, looking up a restaurant and exploring an area do not count. Limits reset at midnight UTC. Seemor only receives what Claude sends it for the request: your ask and the restaurant or place in question. It never sees your chat history. It cannot book tables, confirm opening hours or guarantee allergy safety; its grades come from reviews and menus, not visits. Setup and details: www.seemor.ai/claude
Anthropic’s own published signals, snapshot of November 4, 2026; units undocumented — treat as ordinal.
Over time
Details
Tools(6)
- ask_about_restaurant
- explore_area
- find_restaurant
- lookup_restaurant
- recommend
- search_restaurants
Data from Claude’s public directory API, snapshotted daily by the MCP App Tracker. A listing describes what the directory publishes — not an endorsement.