VeryChic Hotel Deals
Server Details
Unofficial read-only MCP server for VeryChic hotel offers
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- jordantete/verychic-mcp
- GitHub Stars
- 1
- Server Listing
- verychic-mcp
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.9/5 across 2 of 2 tools scored.
The two tools have clearly distinct purposes: one searches and filters offers, the other retrieves full details for a specific offer. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern with snake_case ('verychic_search_offers', 'verychic_offer_details'), making them predictable and readable.
Only two tools is too few for a hotel deals server; typical MCP servers in this domain have more operations like booking, filtering by dates, or managing user preferences. The scope feels thin.
The server only covers search and detail retrieval, lacking obvious operations like booking, date-range filtering, or user account management. This is significantly incomplete for a full hotel deals workflow.
Available Tools
2 toolsverychic_offer_detailsARead-onlyIdempotentInspect
Get full details plus per-date availability and prices for one specific VeryChic offer.
When to use: after `verychic_search_offers` returned an offer you want to inspect —
pass that offer's `source` and `external_id` here. You must obtain those two
identifiers from a search result first; this tool does not search.
Behaviour: read-only and anonymous; rate-limited to about 1 request per second;
prices in EUR, text in French. Availability is looked up for roughly the next 5
months. For tour-operator packages (`source` = 'ORCHESTRA_TO') VeryChic exposes no
date-availability endpoint: `availabilities` is then empty and
`availabilities_supported` is false — meaning "not supported", NOT "sold out".
Returns an object with: `offer` (same fields as a search result, plus `offer_url`),
`advantages`, `included_added_values`, `non_included_added_values`, `gallery`
(image URLs), `availabilities` (one entry per check-in date with `date`, `price`,
`currency`, `nights`, `days`, `departure_city_code`), `availabilities_supported`
(bool), and `cheapest_price` (lowest available price, or null when none).
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | The offer's source type, copied verbatim from the `source` field of a `verychic_search_offers` result. One of 'ORCHESTRA' (a single hotel) or 'ORCHESTRA_TO' (a tour-operator package). Packages have no per-date availability. | |
| external_id | Yes | The offer's numeric `external_id`, copied from a `verychic_search_offers` result. Identifies the offer together with `source`. |
Output Schema
| Name | Required | Description |
|---|---|---|
| offer | Yes | |
| gallery | Yes | |
| advantages | Yes | |
| availabilities | Yes | |
| cheapest_price | Yes | |
| included_added_values | Yes | |
| availabilities_supported | Yes | |
| non_included_added_values | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds significant behavioral context: 'read-only and anonymous; rate-limited to about 1 request per second; prices in EUR, text in French. Availability is looked up for roughly the next 5 months. For tour-operator packages... availabilities is then empty and availabilities_supported is false — meaning "not supported", NOT "sold out".' No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections: main purpose, when to use, behaviour, return value. It is appropriately sized with no wasted sentences; every part adds necessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the output schema not being shown, the description lists all expected return keys comprehensively. The tool has only two required parameters, which are fully explained. The description covers usage, behaviour, edge cases, and output structure completely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the possible source values ('ORCHESTRA' or 'ORCHESTRA_TO') and their implications for availability, as well as reiterating that identifiers come from search results. This justifies a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get full details plus per-date availability and prices for one specific VeryChic offer.' It specifies the verb ('Get'), the resource ('full details plus per-date availability and prices'), and distinguishes it from the sibling tool 'verychic_search_offers' by noting it is for one specific offer after search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says: 'When to use: after verychic_search_offers returned an offer you want to inspect — pass that offer's source and external_id here. You must obtain those two identifiers from a search result first; this tool does not search.' This provides clear context, prerequisites, and exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verychic_search_offersARead-onlyIdempotentInspect
Search and filter the current VeryChic offers by destination, country, price, discount, stars, flights, theme, or proximity — with optional sorting.
When to use: when you already know roughly what the user wants — a place, a country,
a budget, a minimum discount or star rating, flights vs hotel-only, a theme (e.g.
pool, spa, romantic, last_minute), or hotels near a point (near_lat/near_lng, with an
optional radius_km). To inspect one specific offer in depth use
`verychic_offer_details`. All filters are optional and combine with AND; call it with
no filter to browse the full current catalogue in catalogue order.
Behaviour: read-only and anonymous; rate-limited to about 1 request per second.
Filtering is done client-side over the live catalogue: `destination` is a
case-insensitive substring (matched on destination or name), `country` is an exact
case-insensitive match, `max_price`/`min_discount`/`min_stars` are numeric bounds,
`flights_included` toggles flight-bearing vs hotel-only, and `theme` matches a curated
label decoded from the catalogue's thematics tags. Use `sort_by` to order results
(`discount`, `price`, `rating`, `stars`, or `distance`). Prices are in EUR and text is
in French; there is no pagination. Returns the first `limit` matches after filtering
and sorting. "Current" means live offers at call time; the catalogue changes over time.
Returns a list of offer objects (same `source` + `external_id` pair for use with
`verychic_offer_details`). Each offer also carries `discount` (percent off, may be
null), `stars` (1-5, may be null), `price_label` (human-readable price unit, e.g.
"à partir de par pers. pour 3 nuits" vs "par chambre" — read this before comparing
prices), `price_with_flights` (EUR, null when not applicable), `flights_included`
(bool), `rating` (hotel grade, often null in the catalogue), and `themes` (curated
theme labels decoded from the catalogue's thematics tags, e.g. ["pool", "luxury"]).
An empty list means no offer matched the filters.
Proximity search: pass `near_lat` and `near_lng` (decimal degrees, together) to
compute each offer's `distance_km` from that point; add `radius_km` to keep only
offers within that distance, and/or `sort_by="distance"` for nearest-first.
`distance_km` is null when no center is given.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of matching offers to return (default 20), applied after filtering and sorting. No pagination. | |
| theme | No | Keep only offers matching this curated theme, decoded from the catalogue's thematics tags. One of: adults_only, city_break, cruise, island, last_minute, luxury, mountain, nature, pool, romantic, rooftop, spa, sun, villa. Omit to not filter by theme. | |
| country | No | Exact country name, case-insensitive, as spelled in the (French) catalogue, e.g. 'France', 'Italie', 'Grece'. Omit to not filter by country. | |
| sort_by | No | Sort the results: 'discount' (biggest discount first), 'price' (cheapest first), 'rating' (best-rated first), 'stars' (most stars first), 'distance' (nearest first, requires near_lat/near_lng). Offers missing the sort value are placed last. Omit to keep catalogue order. | |
| near_lat | No | Latitude of a search center for proximity search, in decimal degrees. Must be given together with near_lng. Omit for no geo search. | |
| near_lng | No | Longitude of a search center for proximity search, in decimal degrees. Must be given together with near_lat. Omit for no geo search. | |
| max_price | No | Inclusive upper bound on the offer price, in EUR. Offers with no price are excluded when this is set. Omit for no price cap. | |
| min_stars | No | Keep only offers with at least this hotel star rating (1-5), parsed from the offer name. Offers with no detectable rating are excluded. Omit to not filter by stars. | |
| radius_km | No | Keep only offers within this many kilometers of the near_lat/near_lng center. Requires near_lat and near_lng. Omit for no radius. | |
| destination | No | Case-insensitive substring matched against each offer's destination AND name (e.g. 'paris', 'maldives', 'crete'). Omit to not filter by destination. | |
| min_discount | No | Keep only offers whose discount percentage is at least this value (e.g. 40 for '40% off or more'). Offers with no discount are excluded. Omit for no discount filter. | |
| flights_included | No | Filter on whether flights are part of the offer: true keeps flight-bearing offers, false keeps hotel-only offers. Omit to not filter. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), the description adds: read-only and anonymous behavior, rate limiting (~1 req/s), client-side filtering, detailed parameter behaviors (case-insensitivity, numeric bounds, missing value handling), language and currency notes, and no pagination. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections: general purpose, when-to-use, behavioral details, and proximity search. However, it is lengthy (4 paragraphs). While justified by the complexity of 12 parameters, some repetition (e.g., 'read-only and anonymous' could be inferred from annotations) prevents a perfect 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 12 optional parameters, output schema existence, and annotations, the description fully covers all aspects: parameter behaviors, filtering logic (AND combination), sorting, proximity details, missing value handling, return format (list of offers), and special cases (empty list means no matches). It is comprehensive for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant meaning: for destination (substring on name+destination), country (exact case-insensitive), max_price (inclusive, excludes null prices), min_stars (parsed from name, excludes null), flights_included (boolean toggle), sort_by (each value defined), proximity (lat/lng together, radius). It enriches beyond schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search and filter the current VeryChic offers' with specific verbs and resources. It explicitly distinguishes from the sibling tool verychic_offer_details, which is for inspecting a specific offer in depth.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'When to use' section clearly indicates this tool is appropriate when the user has rough criteria, and directs to verychic_offer_details for specific offers. It notes that all filters are optional and combining with AND, plus that calling with no filter browses the full catalogue.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Your Connectors
Sign in to create a connector for this server.