ZBS Index What actually exists in applied AI, with the source next to it

mcp server

1stay

Hotel booking MCP server. Search, book, and manage reservations across 250K+ properties worldwide.

Description as published by the maintainer. Source

  • version 1.0.0
  • active
  • retrieval

active — Most recent push to the repository was 2026-08-03. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

8 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

book_hotel(guests, check_in, hotel_id, check_out, rate_code, external_reference_id)
Book a hotel room. Returns a secure checkout URL where the guest enters all personal and payment details. Do not ask for or collect the guest's name, email address, phone number, credit card number, payment information, or billing details in conversation. After the hotel, rate, dates, and guest count are selected, call this tool and give the guest the secure checkout URL. Guest pays the hotel directly. Their credit card statement shows the hotel name, not 1Stay. Hotel's own confirmation number. Loyalty points apply automatically. A 1Stay Booking Fee is added at checkout. Requires rate_code from get_hotel_details (expires in approximately 15 minutes). If expired, call get_hotel_details again for a fresh code. Required: hotel_id, rate_code, check_in, check_out, guests.
cancel_booking(last_name, first_name, cancellation_token, confirmation_number)
Cancel a hotel reservation. This is a two-step, server-confirmed action. Call 1 — provide guest first name, last name, and hotel confirmation number, and leave cancellation_token empty. The tool verifies the guest's identity and returns the cancellation terms (penalty, refundable amount, free-cancellation deadline, and a warning if the rate is non-refundable) plus a single-use cancellation_token. Nothing is cancelled yet. Call 2 — call again with the same details and the cancellation_token to execute the cancellation. The token is single-use and expires in about 10 minutes. Share the terms with the guest and get their confirmation before the second call. Non-refundable rates forfeit the full amount. Cancellation confirmation is emailed to the address on file. Required: first_name, last_name, confirmation_number.
get_booking(booking_id, verification_token)
Look up a reservation by booking ID (stk_bk_xxxx) or hotel confirmation number. Returns full booking details including hotel, dates, guest info, rate, and status. Guest-facing (anonymous) callers must first call lookup_booking to verify the guest's identity — that returns a verification_token, which you then pass here. Without a valid token, this tool returns no booking data. Developers authenticated with their own API key do not need a token; their access is scoped to their own bookings. Required: booking_id.
get_hotel_details(rooms, guests, check_in, hotel_id, check_out, accessible)
Get rates and room details for a specific hotel. Returns room types, live rates, amenities, cancellation policies, and rate_codes required by book_hotel. Guest pays the hotel directly. Rates shown are what the hotel charges. A 1Stay Booking Fee is added at checkout. Loyalty points eligible. Room type notes: "Run of house" means the hotel assigns the room at check-in. "Suite" at select-service brands usually means a larger room with a sofa, not a separate bedroom. Non-refundable rates are cheaper but cannot be changed or canceled. Required: hotel_id, check_in, check_out.
lookup_booking(email, last_name, first_name, check_in_date, last_four_card, confirmation_number)
Look up a reservation by verifying the guest's identity. Returns the confirmation number and booking summary in conversation. Required before calling: 1. Guest full name (first and last) 2. ONE of: the hotel confirmation number, OR the last 4 digits of the card used to book together with the check-in date An email address is NOT a verification factor. It may be supplied in addition and will be matched, but a name and an email alone will not return a reservation. Do not call this tool without the guest's full name and one of the two factors above. If the guest cannot provide either, their reservation cannot be looked up — this is for the security of their booking, and no other detail substitutes. To resend the confirmation email, use resend_confirmation after verifying identity with this tool. To cancel, use cancel_booking. Required: first_name, last_name.
resend_confirmation(confirmation_number)
Resend a hotel reservation confirmation email. Use after verifying the guest's identity with lookup_booking. The confirmation is always sent to the email address on the booking record. There is no way to redirect it to a different address. If the guest can no longer access that inbox, direct them to support at https://stayker.com/service — a different address cannot be set through this tool. Required: confirmation_number.
search_hotels(rooms, cursor, radius, check_in, currency, latitude, location, check_out, longitude, search_id, max_results, guests_per_room)
Search and book hotels by location and dates. Returns available properties with nightly rates across major brands, boutique, and independent hotels. Guest pays the hotel directly. Hotel's own confirmation number. Loyalty points apply. Required: check_in, check_out.
search_tools(keyword)
List available 1Stay hotel booking tools. Filter by keyword: search, book, cancel, details. Omit keyword to list all tools.

Last successful function declaration observed on . Source: https://mcp.stayker.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcp.stayker.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 2 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-03 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 2 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 1.0.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-03-18 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-03-18 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 8 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcp.stayker.com
mcp endpoint status ok The server listed 8 functions when asked. as of probe mcp.stayker.com

Where to get it

Related, by what their authors tagged them

  • Verified Repo Memory — last commit 2026-02-21, shares agent, agentic-ai, agents
    Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).
  • ai.smithery/docfork-mcp — archived, last commit 2026-06-13, shares agent, agents
    @latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
  • com.docfork/docfork-mcp — archived, last commit 2026-06-13, shares agent, agents
    Up-to-date docs for AI. DEPRECATED: Use io.github.docfork/docfork instead.
  • io.github.docfork/docfork — archived, last commit 2026-06-13, shares agent, agents
    Up-to-date Docs for AI Agents.
  • KTA-Oracle — last commit 2026-04-16, shares agent, agents
    Live KTA rates, market data, payment rails, AML/VAT compliance, SDK snippets. 16 tools.
  • MCP Toolbox for Databases — last commit 2026-08-08, shares agent, agents
    MCP Toolbox for Databases enables your agent to connect to your database.
  • MCP Toolbox for Databases — last commit 2026-08-08, shares agent, agents
    MCP Toolbox for Databases enables your agent to connect to your database.
  • Chiplab — last commit 2026-08-06, shares agent, agentic-ai
    Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
  • conorluddy-ios-simulator-skill-ios-simulator-skill — last commit 2026-06-18, shares agent, agentic-ai
    29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build autom…
  • huangjia2019-claude-code-engineering-api-conventions — last commit 2026-07-23, shares agent, agentic-ai
    API design patterns and conventions for this project. Covers RESTful URL naming, response format standards, error handl…

These share tags the maintainers applied themselves, such as agent, agentic-ai, agents. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent, agent-skills, agentic-ai, agents, mcp, mcp-server.

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. STAYKER-COM/1Stay-mcp on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://mcp.stayker.com/mcp — mcp.stayker.com, observed , trust tier 4.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.