foodeist
Registry code: 7127a5922465acb6
Foodeist (foodeist.com) is a restaurant guide covering about 3.7 million restaurants worldwide, with the richest data (reviews, menus, hours) in the US. Ratings combine Google, Tripadvisor and Yelp reviews; "foodeist_score" and "city_rank" are Foodeist's own ranking within a city. Typical flow: top_restaurants (city + optional cuisine) or restaurants_nearby (coordinates) to get candidates, then get_restaurant / get_menu for details. search_restaurants finds a place by name. Cities can be passed as a name ("Austin, TX", "Paris") or a slug from find_cities. Always link the "url" field when you…
- endpoint
- https://foodeist.com/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is foodeist live?
- Yes — it answered the hub's last check (checked 22h ago). It answered 100% of checks over the last 30 days.
- Is foodeist free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does foodeist have?
- 8 tools: top_restaurants, get_restaurant, fetch, search, find_cities, search_restaurants, restaurants_nearby, get_menu.
- Is foodeist safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 8 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
top_restaurants unknown never probed
Best-ranked restaurants in a city by the Foodeist ranking, optionally only one cuisine. Answers "best X in Y" questions.
{ "type": "object", "required": [ "city" ], "properties": { "city": { "type": "string", "description": "City name (\"Austin, TX\", \"London\", \"Paris, France\") or a city slug from find_cities (\"austin-tx\")." }, "limit": { "type": "integer", "default": 10, "maximum": 30, "minimum": 1, "description": "How many results (default 10, max 30)." }, "cuisine": { "type": "string", "description": "Cuisine or dish type, e.g. \"pizza\", \"sushi\", \"mexican\", \"steakhouse\", \"vegan\", \"coffee\"." } }, "additionalProperties": false }arguments 24 linesget_restaurant unknown never probed
Everything Foodeist knows about one restaurant: address, phone, website, ratings by source, price level, cuisines, weekly hours and open-now, delivery services, description, what reviewers praise and complain about, menu sections.
{ "type": "object", "required": [ "restaurant" ], "properties": { "restaurant": { "type": "string", "description": "Restaurant slug, numeric id, or foodeist.com/place/... URL, as returned by the other tools." } }, "additionalProperties": false }arguments 13 linesfetch unknown 22h ago
Full text profile of one restaurant (details, hours, review summary, menu highlights) by the id that search returned.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "description": "Restaurant id from search (a slug)." } }, "additionalProperties": false }arguments 13 linessearch unknown never probed
Free-text search over Foodeist restaurants. Understands "<cuisine or name> in <city>" ("best tacos in Austin", "Joe's Pizza in New York") and plain restaurant names. Returns ids to pass to fetch. Prefer top_restaurants / search_restaurants when you can fill their fields.
{ "type": "object", "required": [ "query" ], "properties": { "query": { "type": "string", "description": "What the user is looking for." } }, "additionalProperties": false }arguments 13 linesfind_cities unknown 22h ago
Look up cities Foodeist covers by name. Use it to disambiguate ("Portland" → Oregon or Maine) and get the slug for other tools.
{ "type": "object", "required": [ "query" ], "properties": { "limit": { "type": "integer", "default": 5, "maximum": 10, "minimum": 1, "description": "How many results (default 5, max 10)." }, "query": { "type": "string", "description": "City name or its beginning." } }, "additionalProperties": false }arguments 20 linessearch_restaurants unknown never probed
Find restaurants by (part of) their name, optionally inside one city. Use for "is X any good", "what time does X close".
{ "type": "object", "required": [ "name" ], "properties": { "city": { "type": "string", "description": "City name (\"Austin, TX\", \"London\", \"Paris, France\") or a city slug from find_cities (\"austin-tx\")." }, "name": { "type": "string", "description": "Restaurant name, e.g. \"Franklin Barbecue\"." }, "limit": { "type": "integer", "default": 5, "maximum": 20, "minimum": 1, "description": "How many results (default 5, max 20)." } }, "additionalProperties": false }arguments 24 linesrestaurants_nearby unknown never probed
Restaurants around coordinates, best first (or nearest first). Use when the user gives a location, address you can geocode, or "near me" with coordinates.
{ "type": "object", "required": [ "lat", "lng" ], "properties": { "lat": { "type": "number", "maximum": 90, "minimum": -90 }, "lng": { "type": "number", "maximum": 180, "minimum": -180 }, "sort": { "enum": [ "best", "distance" ], "type": "string", "default": "best" }, "limit": { "type": "integer", "default": 10, "maximum": 30, "minimum": 1, "description": "How many results (default 10, max 30)." }, "cuisine": { "type": "string", "description": "Cuisine or dish type, e.g. \"pizza\", \"sushi\", \"mexican\", \"steakhouse\", \"vegan\", \"coffee\"." }, "open_now": { "type": "boolean", "description": "Only places open right now (by their local time)." }, "radius_m": { "type": "integer", "default": 1500, "maximum": 10000, "minimum": 100, "description": "Search radius in meters (default 1500, max 10000)." } }, "additionalProperties": false }arguments 50 linesget_menu unknown 22h ago
Menu of one restaurant: sections, dishes, prices, descriptions. Filter by a section or dish keyword to keep it short.
{ "type": "object", "required": [ "restaurant" ], "properties": { "search": { "type": "string", "description": "Only sections or dishes containing this text, e.g. \"vegan\", \"burger\", \"dessert\"." }, "max_items": { "type": "integer", "default": 120, "maximum": 400, "minimum": 1 }, "restaurant": { "type": "string", "description": "Restaurant slug, numeric id, or foodeist.com/place/... URL, as returned by the other tools." } }, "additionalProperties": false }arguments 23 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id7127a5922465acb6.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/7127a5922465acb6/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/7127a5922465acb6?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.