Remy Research MCP
Server Details
UAE research-use-only catalogue, AED quotes and buyer-reviewed checkout links. No order submission.
- Status
- Healthy
- Uptime
- 100.0% over 17 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
search_products is clearly distinct, but quote_basket and prepare_checkout share nearly identical required fields, stateless basket semantics, and overlapping descriptions. The intended sequence (quote first, then checkout prep) is explained, but an agent could still confuse the two basket tools.
All three tools use a consistent snake_case verb_noun pattern: search_products, quote_basket, prepare_checkout. The convention is predictable and readable.
Three tools is slightly thin but appropriate for a narrow research-catalogue flow: search products, quote a basket, and prepare checkout. Each tool has a clear role in that workflow.
The surface covers product search, quoting, and checkout preparation, but lacks order submission, payment, order status, or quote retrieval. Some gaps may be intentional because checkout and payment happen externally, but the toolset still feels incomplete for the full purchase lifecycle.
Available Tools
3 toolsprepare_checkoutARead-onlyIdempotentInspect
For quote_basket and prepare_checkout only. Required on every call: country (AE), emirate (buyer-selected destination) and items (the complete basket). Each item requires id and qty. Ask the buyer for any missing destination or quantity before calling; use search_products to resolve exact orderable product IDs. Never guess missing values. Return a buyer review link for a valid UAE basket. For Research Use Only. This research-use-only catalogue is for buyers 21+ years of age and is supplied for research purposes only. Not for human or veterinary use. Optional buyer name, phone, email and address may be supplied for prefill only. The link contains those details and must be shared only with the buyer. Creates NO order. Buyer must open the link, review or correct details, accept terms and personally confirm. Card payment link follows by WhatsApp. Send these fields inside tools/call params.arguments. Both basket tools are stateless: send the complete basket again, combining duplicate IDs. Do not send prices, totals, consent or approval flags. If a call returns INVALID_ARGUMENTS, follow missingFields (when present) and nextAction; correct invalid values or collect missing information before retrying with the complete basket. Dubai and qty 1 are examples, not defaults; replace them with the buyer-selected emirate and quantity, and replace PRODUCT_ID_FROM_SEARCH with an orderable id from search. Quote first and resolve blockers, then send the same complete basket here. No cart, session or quote ID is accepted. Buyer prefill is optional and must be nested inside buyer. Example arguments: {"country":"AE","emirate":"Dubai","items":[{"id":"PRODUCT_ID_FROM_SEARCH","qty":1}]}
| Name | Required | Description | Default |
|---|---|---|---|
| buyer | No | Optional buyer-supplied prefill, accepted only by prepare_checkout. Omit if not supplied. No payment, consent or approval fields. The resulting link contains these details and is not encrypted; share only with the buyer. | |
| items | Yes | Required COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call. | |
| country | Yes | Required delivery country code: AE means United Arab Emirates. | |
| emirate | Yes | Required buyer-selected destination. Use an exact listed emirate; ask the buyer if unknown, never assume Dubai. | |
| promoCode | No | Optional buyer-supplied promotion code, up to 24 letters or digits. Omit when absent; do not invent one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds substantial context beyond the annotations: the tool creates no order, the returned link contains unencrypted buyer PII and must be shared only with the buyer, payment follows by WhatsApp after the buyer personally confirms, and the tool is stateless (full basket resent, duplicates combined). None of this contradicts readOnlyHint/idempotentHint — a link-generating, non-mutating preview is consistent with them.
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 critical constraints — required fields, ask-before-calling, no order created, statelessness — are front-loaded and a concrete example anchors the shape. It is dense but long, with some redundancy (the buyer-link/PII warning is restated, and prefill rules repeat in both prose and schema), so not a 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?
Covers everything an agent needs for a 5-param nested-object call with no output schema: what is returned (a review link), what it contains, who may receive it, what not to send, how to recover from INVALID_ARGUMENTS, and where prefill data goes. Nothing material is left to inference.
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%, so the baseline is 3; the description still earns a bump by warning that Dubai and qty 1 in the example are illustrations rather than defaults, that duplicate IDs must be combined into one line, and that buyer prefill must be nested. It does not add much beyond the already-rich per-field descriptions, so it stops short of 5.
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?
States a specific verb+resource: prepares a buyer review link for a valid UAE basket, and explicitly says it 'Creates NO order.' It separates itself from the siblings by naming quote_basket (quote first) and search_products (resolve orderable IDs), so an agent can route without opening a schema.
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?
Explicit sequencing ('Quote first and resolve blockers, then send the same complete basket here'), explicit exclusions ('No cart, session or quote ID is accepted'; 'Do not send prices, totals, consent or approval flags'), explicit pre-call collection rules ('Ask the buyer for any missing destination or quantity'), and error handling guidance via missingFields/nextAction on INVALID_ARGUMENTS.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
quote_basketARead-onlyIdempotentInspect
For quote_basket and prepare_checkout only. Required on every call: country (AE), emirate (buyer-selected destination) and items (the complete basket). Each item requires id and qty. Ask the buyer for any missing destination or quantity before calling; use search_products to resolve exact orderable product IDs. Never guess missing values. Create or update a quote by supplying the COMPLETE desired basket. Add/remove/change items in that list and call again. UAE only. For Research Use Only. This research-use-only catalogue is for buyers 21+ years of age and is supplied for research purposes only. Not for human or veterinary use. Includes the selected emirate’s delivery estimate, cutoff and fee explanation. Does not store or submit an order. Send these fields inside tools/call params.arguments. Both basket tools are stateless: send the complete basket again, combining duplicate IDs. Do not send prices, totals, consent or approval flags. If a call returns INVALID_ARGUMENTS, follow missingFields (when present) and nextAction; correct invalid values or collect missing information before retrying with the complete basket. Dubai and qty 1 are examples, not defaults; replace them with the buyer-selected emirate and quantity, and replace PRODUCT_ID_FROM_SEARCH with an orderable id from search. Do not send buyer details to quote_basket. Example arguments: {"country":"AE","emirate":"Dubai","items":[{"id":"PRODUCT_ID_FROM_SEARCH","qty":1}]}
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Required COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call. | |
| country | Yes | Required delivery country code: AE means United Arab Emirates. | |
| emirate | Yes | Required buyer-selected destination. Use an exact listed emirate; ask the buyer if unknown, never assume Dubai. | |
| promoCode | No | Optional buyer-supplied promotion code, up to 24 letters or digits. Omit when absent; do not invent one. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, which is potentially in tension with 'Create or update a quote', but the description resolves this by stating it is stateless and does not store or submit an order. It further discloses the error contract (INVALID_ARGUMENTS with missingFields and nextAction), what not to send (prices, totals, consent flags), and what comes back (delivery estimate, cutoff, fee explanation).
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 required-fields guidance is front-loaded, but the text is long and repeats the research-use-only restriction twice in near-identical wording ('For Research Use Only' and 'This research-use-only catalogue is for buyers 21+...'). Multiple sentences overlap on statelessness and the complete-basket rule.
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?
For a stateless 4-parameter tool with no output schema, this covers required inputs, error recovery, statelessness, and the returned delivery estimate and fee information. The only weak spot is the ambiguous opening clause, which does not clarify when this tool rather than prepare_checkout is the right terminal call.
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%, so the baseline is 3, but the description adds real semantics: the basket must be complete and duplicate IDs combined, the example values are not defaults, and buyer-derived values must never be guessed. It omits promoCode entirely, leaving that parameter to the schema alone.
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 sentence 'Create or update a quote by supplying the COMPLETE desired basket' gives a specific verb and resource, and the description separates it from prepare_checkout ('Does not store or submit an order'). The opening phrase 'For quote_basket and prepare_checkout only' is confusing and restates the tool name rather than adding scope information.
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?
It explicitly routes the agent: use search_products to resolve orderable IDs, ask the buyer for missing destination or quantity, never guess, UAE only, and re-send the complete basket on updates. It also names a hard exclusion ('Do not send buyer details to quote_basket') and a sibling boundary against prepare_checkout.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_productsARead-onlyIdempotentInspect
Search public product variants by query, compound, format, brand, inStockOnly and inclusive single-unit AED price bounds. Results rank exact matches first and include strength, volume, storage guidance and batch-report evidence with unknowns explicit. For Research Use Only. This research-use-only catalogue is for buyers 21+ years of age and is supplied for research purposes only. Not for human or veterinary use. Return exact id values to the basket tools; sku, name and URL are not basket IDs. No personal information required.
| Name | Required | Description | Default |
|---|---|---|---|
| brand | No | Exact catalogue brand name, case-insensitive, e.g. ProPeptide. | |
| limit | No | Maximum products returned, 1–50. Default 20. | |
| query | No | Optional product text or compound alias. Exact IDs/names rank first. Never include personal information. | |
| format | No | Product format. vial includes vial kits; kit amounts remain explicit in strength.label. | |
| offset | No | Start at 0 or use nextOffset. Keep filters unchanged across pages. | |
| compound | No | Exact compound name, ID or documented alias, e.g. BPC-157 or bpc157. Includes blends containing that compound. | |
| inStockOnly | No | Return only currently orderable, in-stock variants. Defaults to false. | |
| maxPriceAed | No | Inclusive maximum single-unit AED price, before discounts/delivery. | |
| minPriceAed | No | Inclusive minimum single-unit AED price, before discounts/delivery. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine behavioral detail beyond that: results rank exact matches first and include strength, volume, storage guidance and batch-report evidence with unknowns made explicit. The RUO/21+ notices are policy context rather than operational behavior, which keeps this short of a 5.
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 purpose and result behavior are front-loaded well, but the legal block is redundant, restating research-use-only three times ('For Research Use Only', 'research-use-only catalogue... supplied for research purposes only', 'Not for human or veterinary use'). That padding dilutes an otherwise tight description.
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?
With no output schema, the description usefully covers what comes back (ranked results, strength, volume, storage, batch evidence), how ids should be reused, and policy constraints. Pagination semantics for limit/offset exist only in the schema, but with 100% coverage that gap is minor.
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 every parameter is already documented with types, bounds and formats; the description's parameter list largely restates that. It adds no new syntax or interaction rules (e.g. how price bounds combine with inStockOnly) beyond what the schema gives, so the baseline 3 applies.
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?
States a specific verb and resource ('Search public product variants') and enumerates the exact filter dimensions it accepts. It also disambiguates from the sibling basket tools by stating that only exact id values feed the basket tools, so an agent can place it in the workflow without opening a schema.
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?
Gives clear context for use (catalogue search whose exact ids are the input to basket tools) and a concrete negative rule ('sku, name and URL are not basket IDs'). It does not specify when an agent should prefer compound vs query vs brand filters, so guidance is contextual rather than prescriptive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- Changed
prepare_checkout3 fields changed- changed
Input schema / properties / items / descriptionPrevious value: -"The COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call."New value: +"Required COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call." - changed
Input schema / properties / items / items / properties / id / descriptionPrevious value: -"Exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant."New value: +"Required exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant." - changed
Input schema / properties / items / items / properties / qty / descriptionPrevious value: -"Quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity."New value: +"Required buyer-selected quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity. Ask the buyer if unknown; there is no default quantity."
- Changed
quote_basket3 fields changed- changed
Input schema / properties / items / descriptionPrevious value: -"The COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call."New value: +"Required COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call." - changed
Input schema / properties / items / items / properties / id / descriptionPrevious value: -"Exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant."New value: +"Required exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant." - changed
Input schema / properties / items / items / properties / qty / descriptionPrevious value: -"Quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity."New value: +"Required buyer-selected quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity. Ask the buyer if unknown; there is no default quantity."
1 tool update
- Changed
search_products9 fields changed- added
Input schema / properties / brandAdded value: +{ + "description": "Exact catalogue brand name, case-insensitive, e.g. ProPeptide.", + "maxLength": 80, + "minLength": 1, + "type": "string" +} - added
Input schema / properties / compoundAdded value: +{ + "description": "Exact compound name, ID or documented alias, e.g. BPC-157 or bpc157. Includes blends containing that compound.", + "maxLength": 120, + "minLength": 1, + "type": "string" +} - added
Input schema / properties / formatAdded value: +{ + "description": "Product format. vial includes vial kits; kit amounts remain explicit in strength.label.", + "enum": [ + "vial", + "pen" + ], + "type": "string" +} - added
Input schema / properties / inStockOnlyAdded value: +{ + "description": "Return only currently orderable, in-stock variants. Defaults to false.", + "type": "boolean" +} - changed
Input schema / properties / limit / descriptionPrevious value: -"Maximum products to return, as a JSON integer from 1 to 50."New value: +"Maximum products returned, 1–50. Default 20." - added
Input schema / properties / maxPriceAedAdded value: +{ + "description": "Inclusive maximum single-unit AED price, before discounts/delivery.", + "minimum": 0, + "type": "number" +} - added
Input schema / properties / minPriceAedAdded value: +{ + "description": "Inclusive minimum single-unit AED price, before discounts/delivery.", + "minimum": 0, + "type": "number" +} - changed
Input schema / properties / offset / descriptionPrevious value: -"Pagination offset. Start at 0 or use nextOffset from the previous search result."New value: +"Start at 0 or use nextOffset. Keep filters unchanged across pages." - changed
Input schema / properties / query / descriptionPrevious value: -"Optional product search text, up to 120 characters. Omit to browse; never include personal information."New value: +"Optional product text or compound alias. Exact IDs/names rank first. Never include personal information."
3 tool updates
- Changed
prepare_checkout11 fields changed- added
Input schema / properties / buyer / descriptionAdded value: +"Optional buyer-supplied prefill, accepted only by prepare_checkout. Omit if not supplied. No payment, consent or approval fields. The resulting link contains these details and is not encrypted; share only with the buyer." - added
Input schema / properties / buyer / properties / address / descriptionAdded value: +"Optional buyer-supplied address, up to 500 characters; do not invent missing delivery details." - added
Input schema / properties / buyer / properties / email / descriptionAdded value: +"Optional buyer-supplied email, up to 254 characters; use the supplied value as-is." - added
Input schema / properties / buyer / properties / name / descriptionAdded value: +"Optional buyer-supplied name, up to 120 characters; do not infer or invent it." - added
Input schema / properties / buyer / properties / phone / descriptionAdded value: +"Optional buyer-supplied phone, up to 40 characters; use the supplied value as-is." - added
Input schema / properties / country / descriptionAdded value: +"Required delivery country code: AE means United Arab Emirates." - added
Input schema / properties / emirate / descriptionAdded value: +"Required buyer-selected destination. Use an exact listed emirate; ask the buyer if unknown, never assume Dubai." - added
Input schema / properties / items / descriptionAdded value: +"The COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call." - added
Input schema / properties / items / items / properties / id / descriptionAdded value: +"Exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant." - added
Input schema / properties / items / items / properties / qty / descriptionAdded value: +"Quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity." - added
Input schema / properties / promoCode / descriptionAdded value: +"Optional buyer-supplied promotion code, up to 24 letters or digits. Omit when absent; do not invent one."
- Changed
quote_basket6 fields changed- added
Input schema / properties / country / descriptionAdded value: +"Required delivery country code: AE means United Arab Emirates." - added
Input schema / properties / emirate / descriptionAdded value: +"Required buyer-selected destination. Use an exact listed emirate; ask the buyer if unknown, never assume Dubai." - added
Input schema / properties / items / descriptionAdded value: +"The COMPLETE desired basket of 1–20 distinct variant IDs. Combine the same ID into one line; send the entire updated basket on every call." - added
Input schema / properties / items / items / properties / id / descriptionAdded value: +"Exact id from the latest search_products result, not sku, product name or URL. Select an orderable variant." - added
Input schema / properties / items / items / properties / qty / descriptionAdded value: +"Quantity as a JSON integer from 1 to 10, for example 2, not \"2\". The field is qty, not quantity." - added
Input schema / properties / promoCode / descriptionAdded value: +"Optional buyer-supplied promotion code, up to 24 letters or digits. Omit when absent; do not invent one."
- Changed
search_products3 fields changed- added
Input schema / properties / limit / descriptionAdded value: +"Maximum products to return, as a JSON integer from 1 to 50." - added
Input schema / properties / offset / descriptionAdded value: +"Pagination offset. Start at 0 or use nextOffset from the previous search result." - added
Input schema / properties / query / descriptionAdded value: +"Optional product search text, up to 120 characters. Omit to browse; never include personal information."
3 tool updates
- First observed
prepare_checkout - First observed
quote_basket - First observed
search_products
Related MCP Connectors
Find UAE off-plan developments, registered residential sales and research reports.
Read-only UAE legal information: official routes, practical guides, free tools and FAQs.
Fine chemicals sourcing: compounds by name or CAS, suppliers, price ranges, quote links. No key.
Search and cite UAE law (federal, Dubai, Abu Dhabi, DIFC, ADGM) with verifiable citations.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to answer peptide questions from PepBank study summaries with cited sources, and to look up catalog products with variants, prices, stock and per-lot lab reports (COAs). Also covers store policies and generates cart links for checkout on curo.you.7MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to securely search products, obtain signed quotes, create checkouts, and track orders without directly handling prices or payment amounts, enforcing spending policies and audit trails.1-
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to search and retrieve structured peptide research profiles with cited, tier-labelled evidence, safety and regulatory status, and to compare two or three peptides side by side without ranking. Also provides research article and FAQ search, category and trend lookups, plus unit conversion, solution concentration, blend and cost-per-amount calculators, all read-only and anonymous.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to conduct academic research workflows such as paper discovery, literature mapping, citation chasing, author pivots, citation repair, and regulatory or species document retrieval.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.