Neoavis
Server Details
Can an AI agent buy on this French store? 500 stores tested: score, guest checkout, UCP. Free.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Most tools have clearly distinct jobs, and the descriptions explicitly route between similar options. The main possible confusion is among the discovery tools (classement_secteur, trouver_marchands, rechercher_marchand) and between lancer_test and verifier_site, though the 'use when' guidance usually resolves it.
Seven of eight tools use French infinitive verb + noun in snake_case; classement_secteur is noun+noun, and singular/plural varies semantically (marchand/marchands). The pattern is still highly readable and mostly consistent, with only minor deviations.
Eight tools map cleanly onto the domain's workflows: sector ranking, criteria-based discovery, name lookup, store detail, comparison, live machine-readability checking, and async private test start/status. There is no obvious padding or missing count issue.
The surface covers the full public and private testing lifecycle: discovery, ranking, lookup, detail, comparison, free live readability check, and asynchronous private test start/status. Remaining account-management details, such as quota, are exposed in return payloads rather than requiring separate tools.
Available Tools
8 toolsclassement_secteurClassement d'un secteurARead-onlyIdempotentInspect
Ranking of ALL tested French online stores in one sector, best score first. Use it when the user wants the best stores of a sector as a whole (for example the best beauty stores for an AI agent). To filter by proven facts such as guest checkout, use trouver_marchands; for the details of one store, consulter_marchand. Returns: secteur and marchands, a list of every ranked store (30 to 70 per sector) with rang, ex_aequo (equal scores share a rank, then alphabetical order), domaine, nom, note out of 100, nombre_avis, dernier_test, test_ancien and page. Sectors: beaute, mode, maison, sport, epicerie, enfant, animalerie, bijoux, bricolage, high-tech. Unknown sector: error result listing the valid ones.
Inputs: secteur (required), langue.
comparer_marchandsComparer des marchandsARead-onlyIdempotentInspect
Side-by-side test results for two to five French online stores you already know, in the order given. Use it when the user hesitates between specific stores. To find candidates first, use trouver_marchands or rechercher_marchand. Returns: marchands, one full result per store, identical to consulter_marchand (score out of 100, six steps acces to caisse, proven facts, machine readability, UCP checkout, summary and page). Each store counts as one request against the rate limit. Fewer than two or more than five domains: error result.
Inputs: domaines (required), langue.
consulter_marchandConsulter un marchandARead-onlyIdempotentInspect
Full test result for ONE French online store, by domain: what an AI shopping agent managed to do there at the latest test. Use it before visiting, recommending or buying from a French store, or when the user asks if a store works with AI agents. To find stores you do not know yet, use trouver_marchands; to look up a store by name, rechercher_marchand; to put several side by side, comparer_marchands. Returns: note (score out of 100: journey 55, proven purchase facts 30, machine readability 15), etapes (six steps in order — acces, cookies, recherche, fiche, panier, caisse — each reussi, partiel, echec or non_atteint, with a motif when it failed), faits (oui, non or inconnu: checkout without an account, delivered price before sign-up, shipping costs, return policy, third-party seller), machine (product data, robots.txt, llms.txt, sitemap, UCP), ucp_commande (store declares UCP checkout), dernier_test (date), test_ancien (true if older than 90 days), resume (one-sentence summary to quote) and page (link to cite). Unknown or untracked domain: error result, nothing charged, with suites_payantes when available (x402 URLs to check that store live or have it fully tested) and test_prive_agence (the Agency plan: a private full purchase test of that store with lancer_test).
Inputs: domaine (required), langue.
lancer_testLancer un test d'achat privéAInspect
Starts a PRIVATE full purchase test of ANY online store by the Neoavis AI shopping agent: it looks for the product, opens its page, adds it to the cart and goes to checkout, without paying. Requires an Agency plan access key (X-Api-Key header, or ?cle=nk_… in the server URL); each test counts against the key's monthly quota. Use it when the user asks to test, audit or re-test a store (a client's site, a competitor, a check before launch). To read what Neoavis already published about a tracked store, use consulter_marchand (free); for an instant machine-readability check without a purchase journey, use verifier_site (free). Returns: id (test id), statut (en_attente), domaine, produit, dossier (private evidence report page to give the user), resultat (URL of the JSON result), delai (the test runs asynchronously, usually within the hour on business days) and quota (par_mois, utilises, restants, remise_a_zero). Then call lire_test with the id. Error results, never counted against the quota: no key or a key without tests (the answer gives the plan page), monthly quota reached (with the reset date), three tests already pending, invalid site or product. Nothing is published: a private test never changes a public Neoavis page.
Inputs: site (required), langue, produit.
lire_testLire un test d'achat privéARead-onlyIdempotentInspect
State and result of a private purchase test started with lancer_test (or paid per request with x402), by its id. No key needed: the id is the secret. Use it after lancer_test, every few minutes, until statut is termine or echec. For published results of tracked stores, use consulter_marchand instead. Returns: id, statut (en_attente, en_cours, termine or echec), domaine, produit, demande_le, commence_le, termine_le, dossier (private evidence report page: give this link to the user, it holds the screenshots, the proof of each fact and the log of the agent's actions), and once finished resultat: note (score out of 100), etapes (six steps, each reussi, partiel, echec or non_atteint with a motif), faits (oui, non or inconnu), lisibilite, captures and resume (one-sentence summary to quote). A failed test gives message and is not counted against the quota. Unknown id: error result.
Inputs: id (required).
rechercher_marchandRechercher un marchandARead-onlyIdempotentInspect
Find a tracked French store by part of its NAME or DOMAIN, across all sectors (case and accents ignored). Use it when the user names a store but you do not know its exact domain; then call consulter_marchand with the domain found. To discover stores by criteria rather than by name, use trouver_marchands. Returns: requete and marchands, every match (usually a few) with rang in its sector, ex_aequo, secteur, domaine, nom, note out of 100, nombre_avis, dernier_test, test_ancien and page. No match: an empty list, which means the store is not tracked yet.
Inputs: requete (required), langue.
trouver_marchandsTrouver des marchands par critèresARead-onlyIdempotentInspect
Discover French online stores where an AI agent can actually buy, filtered by PROVEN facts, in one sector or all of them. Use it when the user asks where to buy something online in France, which stores allow guest checkout, or which show the delivered price. To look up a store by name, use rechercher_marchand; for a whole sector ranking, classement_secteur. Every filter is optional; set a boolean to true to require that fact. Returns: secteur, criteres (filters applied), total (number of matching stores) and marchands, best score first, at most limite entries, each with rang, ex_aequo, secteur, domaine, nom, note out of 100, the five facts as booleans (sans_compte, prix_livre, frais_livraison, retours, ucp_commande), dernier_test and page. No match: total 0 and an empty list.
Inputs: ucp, langue, limite, retours, +5 more.
verifier_siteVérifier un site en directARead-onlyIdempotentInspect
Live check of ANY online store, tracked by Neoavis or not: can an AI shopping agent read it without clicking? Reads the UCP checkout profile (/.well-known/ucp), structured product data, robots.txt access for shopping agents, llms.txt and sitemap, in a few seconds. Use it when the user wants to buy from a store that consulter_marchand does not know, or wants to know if their own store is ready for AI agents. For a store Neoavis already tested, consulter_marchand gives the full purchase test. Returns: points (out of 15), verdict (pret, partiel or pas_pret), criteres_reussis, neoavis (score out of 100 and page when tracked), resume (one sentence to quote), detail_gratuit_humain (page with the per-criterion detail for a human) suites_payantes (x402 URLs, USDC on Base, no account: per-criterion live check, and a full purchase test) and test_prive_agence (the Agency plan: the full purchase journey tested with lancer_test, delivered as an evidence report). Free: 10 checks per hour per address. Unreadable domain or unreachable site: error result.
Inputs: site (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Is a website ready for AI shopping agents? Readiness score (0-100) + agent shopping simulation.
Free open check: can an AI agent reach checkout on this store? Advisory; ARC stops before payment.
AgentReady.market audit: can an AI shopping agent find, understand and BUY on this store? /100.
Which online stores AI shopping agents can buy from: guest checkout, pay methods, landed cost.
Related MCP Servers
- AlicenseAqualityBmaintenanceFree, rules-based checks for e-commerce product pages: AI shopping readiness (structured data, reviews, return and shipping terms, GTINs, AI crawler access), Google Merchant Center compliance, store SEO audit and Shopify checkout deadlines. No AI calls, nothing stored.24MIT
- AlicenseBqualityCmaintenanceMCP server for auditing product pages to determine AI shopping agent readiness, providing a 0–100 score and actionable fixes.115Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to check whether online stores are reachable at checkout using dated, source-labelled evidence, find stores, and report checkout attempts through hosted Streamable HTTP tools.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to search and compare products across multiple retailers, build carts, and propose purchases that only a human can authorise, with a self-hosted control panel.-
Glama MCP Gateway
Add one secure layer between your agents and this server.