Search / ai.yentaknows/directory
Yenta Directory
R0· no sign-inAnonymous, read-only cross-venue discovery of partner-approved venues, cities, destinations.
v0.1.0 · active · repository · website · descriptor JSON · versions
Search / ai.yentaknows/directory
R0· no sign-inAnonymous, read-only cross-venue discovery of partner-approved venues, cities, destinations.
v0.1.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://yentaknows.ai/mcp"
}
}
}claude mcp add --transport http directory https://yentaknows.ai/mcp[mcp_servers.directory]
url = "https://yentaknows.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"directory": {
"type": "remote",
"url": "https://yentaknows.ai/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://yentaknows.ai/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=directory&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8veWVudGFrbm93cy5haS9tY3AifQ%3D%3D"
}{
"servers": {
"directory": {
"type": "http",
"url": "https://yentaknows.ai/mcp"
}
}
}{
"mcpServers": {
"directory": {
"httpUrl": "https://yentaknows.ai/mcp"
}
}
}extensions:
"directory":
enabled: true
name: "directory"
type: streamable_http
uri: "https://yentaknows.ai/mcp"
timeout: 300
protocol.modernsupports 2026-07-28 (server/discover)protocol.statelessanswers without a sessionprotocol.transportstreamable HTTPprotocol.list_ttltool list is cacheable (ttlMs 60000)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations16 of 16 tools declare readOnlyHint or destructiveHinttools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHinttools.token_costabout 5,002 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes26 tool changes in 30 daysstability.rug_pull10 tools kept their name but changed most of their description in 30 days; review before trusting themdeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packagedestination_facetsremovedList a named destination's valid area, category and tag filter values (the destination's own host calls this list_facets).
venue_linksremovedGet a named venue's published booking and other links (connect to its mcp_endpoint to actually book; the venue's own host calls this get_venue_links).
search_destinationsremovedSearch published travel destinations by name; omit the query to list all, and connect to each result's mcp_endpoint for its listings, events and guides.
destination_listingremovedGet one listing's full detail by its id, including a live linked venue's mcp_endpoint and linked_venue_slug to read or book it via the venue_* tools (the destination's own host calls this get_listing).
venue_dietary_optionsremovedList a named venue's declared dietary tags and allergens — the exact spellings venue_menu_search matches literally (the venue's own host calls this get_dietary_options).
venue_menu_searchremovedSearch a named venue's menu by text, required dietary tags and allergens to avoid; call venue_dietary_options first for the exact spellings (the venue's own host calls this search_menu).
facet_vocabularyremovedThe closed VENUE facet vocabulary (vibe, cuisine, dietary, and more) plus today's live cuisine, price_band and neighbourhood values across published venues, the exact values search_venues' matching filters accept — for a destination's areas, categories and tags call destination_facets instead.
get_destinationremovedGet one published destination's summary and live mcp_endpoint by its slug — always available for any published destination, so use this if destination_overview reports it is not available.
get_venuesremovedGet several published venues' summaries in ONE call by their slugs — the batch counterpart to get_venue, so a shortlist from search_venues needs no per-slug round-trip; the base view (identity, essentials, capabilities, booking, mcp_endpoint) is always returned, while include opts into heavier per-venue reads — hours, dietary (dietary-tag/allergen vocabulary), attributes (facets) and menu_summary — with items coming back in the requested order (a repeated slug resolves once) and not_found listing any requested slug that did not resolve to a published venue.
get_venueremovedGet one published venue's summary, capabilities and live mcp_endpoint by its slug — always available for any published venue, so use this if venue_profile reports the venue is not available.
Showing the latest 10. Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-100% ~updated-40d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://yentaknows.ai/mcp streamable-http | none | yes | 100% | 834 ms | 2026-07-28 | 2026-10-20 |
destination_eventsread-only | Find what is on in a named destination: events from today onwards. A recurring event's dates are its series span, so read its recurrence. Offer booking_url when present; cite canonical_url, the destination's page. |
destination_faqread-only | Answer a question about a named destination from its published FAQs; omit query to read them all. |
destination_guideread-only | Read a named destination's travel guides: weather, getting here, transport, entry requirements, safety and more. Pass topic (from destination_overview guide_topics) to read one subject; page with cursor. |
destination_listingsread-only | Find places to stay, eat and visit in a named destination by text, category, area or tags. Every query word matches, in any order; each business appears once (also_listed_as) with a snippet and map_url, so call it again with listing_id for the full text. An unknown filter value's reason lists the valid ones. |
destination_offersread-only | Find a named destination's current deals and packages, with the partner booking link. Only offers valid on valid_on (today by default) are returned. Offer booking_url when present; cite canonical_url, the destination's page. |
destination_overviewread-only | One call answers what a destination offers and what's on: counts, a few places, next events and guide topics. It counts offers, seasonality and FAQs too, and names the categories and areas listings, events and offers filter by. Drill in with destination_listings / destination_events only if preview.complete is false. |
destination_seasonalityread-only | Get a named destination's best time to visit, weather and wildlife seasons (e.g. whale watching), month by month. |
fetchread-only | Read the full page for one search result id as Markdown text, with its citable url. Ids look like "venue:acme-bistro", "destination:los-cabos" or "listing:los-cabos:1234". |
list_citiesread-only | List the cities that have published restaurants and bars. Travel destinations such as Los Cabos are not cities here; read one with destination_overview. |
searchread-only | Search venues, travel destinations and places inside destinations by name or keyword. Returns results of id, title and url; pass an id to fetch for the full page. For filters use search_venues, search_menus or destination_listings. |
search_menusread-only | Find dishes across all venues by text, city, dietary tags or allergens to avoid. Each item is tagged with its venue, so one call compares venues; for one named venue use venue_menu. |
search_venuesread-only | Find restaurants and bars by city, cuisine, opening time or features. Filters are HARD, prefer_* and avoid are SOFT (rank only), and query is ONE keyword. Each result has slug, capabilities, open_now and distance_km; a place inside a destination is not here, use destination_listings. |
venue_eventsread-only | Find what is on at a named venue: dated events from its local today onwards. Filter by exact event_type if you know it. If not available, check the capabilities venue_profile lists; the venue may not publish this. |
venue_faqread-only | Answer a question about a named venue from its published FAQs; omit query to read them all. If not available, check the capabilities venue_profile lists; the venue may not publish this. |
venue_menuread-only | Find dishes at a named venue, e.g. venue="Acme Bistro", dietary_tags=["vegan"], allergens=["milk"]. Filter by text, tags, allergens or max_price; unfiltered, item lists its dietary tags, example dishes and allergen counts. If not available, check the capabilities venue_profile lists; the venue may not publish this. |
venue_profileread-only | Get a venue's hours, address, map, phone, booking and links by name or slug, e.g. venue="Acme Bistro". It also holds cuisine, attributes, menu_summary and capabilities (the other venue_* tools that answer for it); hours_summary is ready to quote. |
Schemas: list_tools.
{
"name": "ai.yentaknows/directory",
"title": "Yenta Directory",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://yentaknows.ai/mcp",
"type": "streamable-http"
}
],
"version": "0.1.0",
"repository": {
"url": "https://github.com/yenta-ai/yenta-mcp",
"source": "github"
},
"websiteUrl": "https://yentaknows.ai/",
"description": "Anonymous, read-only cross-venue discovery of partner-approved venues, cities, destinations."
}