
Yenta Directory
Anonymous, read-only cross-venue discovery of partner-approved venues, cities, destinations.
What it can do
What data it sees
Do you need an account
No: the server works without sign-in
Anonymous, read-only cross-venue discovery of partner-approved venues, cities, destinations.
How to connect
How to connect Yenta Directory to Claude
The server address to paste into Claude settings:
https://yentaknows.ai/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Yenta Directory to ChatGPT
The server address to paste into ChatGPT settings:
https://yentaknows.ai/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Yenta Directory to Cursor
The server address to paste into Cursor settings:
https://yentaknows.ai/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (21)
Raw names from tools/list. Only developers need these.
| search_venues | Search published venues by name or description, optionally filtered by city, cuisine, price band, neighbourhood, whether the venue takes reservations, proximity (near a lat/long within a radius, nearest first) and opening hours (open on a given day/time, or open now) — all HARD filters that exclude on a miss, plus a HARD experiential-facet filter (facets, '<facet_type>:<value>' tokens from facet_vocabulary) — with prefer_cuisine, prefer_neighbourhood, avoid and prefer_facets as SOFT preferences that only rank a venue up or down and never drop it; each result carries the venue's capabilities and, when it is live, its mcp_endpoint. |
| list_cities | List the cities that have at least one published venue. |
| get_venue | Get one published venue's summary, capabilities and live mcp_endpoint by its slug. |
| get_venues | Get 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. |
| search_destinations | Search 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. |
| search | Search published venues and destinations together in one call, each result tagged with its kind (venue or destination); pass kind to scope to one type, query to match names and venue descriptions, and city to narrow venues, then use search_venues or search_destinations for type-specific filters such as cuisine, hours or area. |
| get_destination | Get one published destination's summary and live mcp_endpoint by its slug. |
| search_menus | Search menu items across all published venues by text, city, required dietary tags and allergens to avoid, each result tagged with its venue so an agent can rank venues in one call. |
| facet_vocabulary | The closed 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. |
| venue_profile | Get a named venue's published profile summary — give its name (and city) or slug. |
| venue_menu_search | Search a named venue's menu by text, required dietary tags and allergens to avoid; call venue_dietary_options first for the exact spellings. |
| venue_dietary_options | List a named venue's declared dietary tags and allergens — the exact spellings venue_menu_search matches literally. |
| venue_faq | Search a named venue's published FAQs, optionally filtered by text. |
| venue_links | Get a named venue's published booking and other links (connect to its mcp_endpoint to actually book). |
| destination_overview | Get a named destination's summary: counts by category, currency, timezone. |
| destination_facets | List a named destination's valid area, category and tag filter values. |
| destination_listings | Search a named destination's listings by text, category, area and tags (slugs from destination_facets); optionally near another listing. |
| destination_listing | Get 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. |
| destination_events | Find a named destination's events overlapping a date window (default from today; a recurring event's span is not a single date — read its recurrence). |
| destination_guide | Read a named destination's editorial guides such as weather, getting here and safety. |
| destination_faq | Search a named destination's FAQs, optionally filtered by text. |