About Asian Recs
Asian Recs is an MCP server for exploring restaurants, cafes, desserts, and bars in San Francisco and New York. It ranks places by Asian diners’ ratings alongside overall ratings, with data refreshed weekly.
Key features
- 01San Francisco and New York listings
- 02Rankings by Asian diners’ ratings
- 03Comparison with overall ratings
- 04Restaurants, cafes, desserts, and bars
- 05Weekly data refresh
Use cases
- 01Find soup dumplings in Flushing
- 02Compare ramen ratings in the East Village
- 03Locate boba by neighborhood
MCP support
The server exposes food and venue lookup through https://asianrecs.com/api/mcp, letting MCP clients search by location, cuisine, and diner ratings.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://asianrecs.com/api/mcpclaude mcp add --transport http com-asianrecs-asianrecs https://asianrecs.com/api/mcp{"mcpServers":{"com-asianrecs-asianrecs":{"type":"http","url":"https://asianrecs.com/api/mcp"}}}Open in Cursor{"servers":{"com-asianrecs-asianrecs":{"type":"http","url":"https://asianrecs.com/api/mcp"}}}Open in VS Code{"mcpServers":{"com-asianrecs-asianrecs":{"type":"http","url":"https://asianrecs.com/api/mcp"}}}{"mcpServers":{"com-asianrecs-asianrecs":{"serverUrl":"https://asianrecs.com/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3| Parameter | Type | Required | Description |
|---|---|---|---|
| city | enum | Yes | sf = San Francisco, nyc = New Yorksf | nyc |
| near | object | No | A point to measure distance from; adds distance_mi to results. |
| near.lat | number | Yes | |
| near.lng | number | Yes | |
| sort | enum | No | asian_rating: Asian diners' rating, highest first; loved_more: Biggest gap above everyone else; most_asian_diners: Most Asian diners; share_asian: Highest share of Asian reviewers; distance: Closest first (needs near). Default asian_rating.asian_rating | loved_more | most_asian_diners | share_asian | distance |
| type | enum | No | Kind of place. Default restaurants. Boba, coffee, tea and bakeries are cafes; ice cream and dessert shops are desserts.restaurants | desserts | cafes | bars |
| limit | integer | No | Default 10. |
| query | string | No | Free text matched against name, cuisine, neighborhood and dishes, e.g. a dish like "soup dumplings". |
| cuisine | string | No | Cuisine or drink category, e.g. "ramen", "sichuan", "korean", "dim sum", or "boba" with type cafes. |
| location | string | No | Neighborhood or area, e.g. "Mission", "East Village", "Flushing", "Manhattan — Downtown". list_filters has the exact names. |
| radius_mi | number | No | With near: only places within this many miles. |
Details
From the project READMEAsian Recs for Claude
Restaurants, desserts, cafes and bars in San Francisco and New York, ranked by how Asian diners rate them beside how everyone else does. Data from asianrecs.com, refreshed weekly.
Claude Code
/plugin marketplace add raymond-raymond/asianrecs-claude
/plugin install asianrecs@asianrecs
Claude.ai and Claude Desktop
Find Asian Recs in the connectors directory, or Settings → Connectors → Add custom connector → https://asianrecs.com/api/mcp
Try
- "Best soup dumplings in Flushing?"
- "Where do Asian diners like ramen more than everyone else in the East Village?"
- "Boba near 24th and Mission"
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.