MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

Escape the Week

Plan and price Friday-to-Monday city weekends in 42 cities, then get a booking plan.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
116 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
16

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 116 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name Escape the Week.

  • Pass
    Lists tools

    tools/list returned 16 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 116 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 116 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    61 of 61 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-10-31T09:53:59.432869Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Escape the Week

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http escape-the-week https://escapetheweek.com/mcp/public

Capabilities

Tools 16

booking_checklist

Booking links and checklist for a weekend, ordered by scarcity: first the steps that must be booked ahead (longest lead time first, each with reserve_days, a book_by date YYYY-MM-DD and an easier fallback), then flights, the hotel and the other bookable steps. An item's alternatives [{provider, url}] are other sites that book the same thing (the hotel on Klook beside Booking.com), not additional items.

Discovered
booking_manifest

The booking plan for one weekend, in booking order: items (flights, hotel and bookable steps; scarcest first) each with kind, title, when (date YYYY-MM-DD and local time HH:MM), the affiliate-tracked partner url with dates, party size and time prefilled where the partner supports it, provider, estimated_cost {cents, currency} for the whole party, reserve_days, book_by (YYYY-MM-DD), fallback and alternatives [{provider, url}]: other sites that book the same item (the hotel on Klook beside Booking.com), not additional items; plus needs_from_user (traveller names, contact, payment approval), a sequence_note, the total estimate in integer cents, cancellation_advice and a disclosure that the links are affiliate links. Escape the Week takes no payment: every booking and payment is made on the partner's site. Prices are estimates, not quotes.

Discovered
estimate_all

Compare published weekends by price (integer cents) for a tier, a month or the year average, a group and an optional origin. By default (detail cities) one row per city: its cheapest persona, min_total_cents and min_per_person_cents. detail all adds a row per (city, persona) with total, per person, flights and the persona's party_shapes, which city and persona narrow. Estimates only, no fare lookups; cached for a minute per parameter set.

Discovered
estimate_itinerary

Budget estimate (integer cents) for a published itinerary: activities, lodging, transport and flights for a tier, a month or the year average, and a group.

Discovered
get_city

Fetch one city by its slug (from list_cities): name, country, region, coordinates, IATA code, currency and the twelve monthly season factors.

Discovered
get_fare

Cheapest known return fare per person between two IATA codes for a Friday-to-Monday weekend (cached from Travelpayouts).

Discovered
get_persona

Fetch one persona by its slug (from list_personas), with its audience.

Discovered
get_published_itinerary

The full published itinerary for one (city, persona): its days and steps with local times (HH:MM), kind, notes, cost_cents per person at the modest tier (integer cents), reserve_days (how many days ahead a hard step must be booked, or null), a fallback, and each step's venue with coordinates and offers. Day 0 is Friday.

Discovered
itinerary_calendar

The published itinerary as iCalendar text for one weekend (Friday = day 0): one event per step at floating local times, no time zone. friday is a YYYY-MM-DD date.

Discovered
list_cities

List the cities that have published weekends, with their slug, IATA airport code, currency and the twelve monthly season factors (1.0 = shoulder season; higher is dearer). Paged.

Discovered
list_origins

List the origins a trip can start from: slug (the origin parameter), name and IATA airport code. Unpaged.

Discovered
list_personas

List the personas (the kind of traveller an itinerary is written for, e.g. foodie or collector) with their slug and audience: party_shapes (solo, couple, friends, family, multigen), children (boolean) and pace (relaxed, steady, brisk). Persona slugs are used with city slugs to name an itinerary. Paged.

Discovered
list_pricing_multipliers

List every price multiplier: for each (tier, dimension) the factor applied to the modest-tier price. Dimensions are sight, culture, dining, lodging, transport and flight.

Discovered
list_pricing_tiers

List the budget tiers in display order (cheap, modest, expensive, luxury, ultra); the name is the tier parameter's value.

Discovered
list_published_itineraries

The public index: every published itinerary with its city and persona slugs, title, summary, names, step counts and the sum of its steps' costs in integer cents (currency EUR unless the city says otherwise). It lists every (city, persona) weekend that exists.

Discovered
submit_tip

Send a tip about a city: a place to add, a closed place, somewhere nearly impossible to book, or a wrong fact. Public. A tip is never published; an editor reviews it first. Rate limited per sender.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected116 ms16