
Neoavis MCP server
Which MCP servers are Neoavis's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namecom.neoavis/constatsverified in the MCP registry
The registry name sits under neoavis.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools5
- Server calls itselfNeoavis
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 221 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "Compare retailers' scores by sector", the likely first call is classement_secteur.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days7 of 7 daily checks
- Median first answer259 ms
- Space in an agent's context≈ 1,745 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Test a merchant site as an AI shopping agent
- can do · Compare retailers' scores by sector
- not sure · Retest a site after fixing checkout problems
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
consulter_marchandWhat an AI agent found when shopping at a French online merchant: score out of 100, six steps, whether it accepts UCP checkout (access, cookies, search, product page, cart, checkout) and five facts. Call it before visiting a merchant…
classement_secteurRanking of the merchants of one sector by what an AI agent manages to do on their site. / Classement des marchands d’un secteur. Sectors / secteurs : beaute, mode, maison, sport, epicerie, enfant, animalerie, bijoux, bricolage, high-tech.
rechercher_marchandFind tracked French merchants by name or domain (case and accents ignored), across all sectors, with their score and page. / Recherche un marchand suivi par son nom ou son domaine.
trouver_marchandsFind French online merchants where an AI agent can actually buy, filtered by proven facts: checkout without an account, delivered price shown, shipping costs, return policy, UCP checkout, minimum score. Sorted by score out of 100. /…
comparer_marchandsCompare two to five French online merchants side by side: score out of 100, six steps, proven facts, machine readability, UCP checkout. / Compare deux à cinq marchands.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"constats": {
"type": "http",
"url": "https://neoavis.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http neoavis https://neoavis.com/api/mcpclaude.ai, ChatGPT and other clients: add https://neoavis.com/api/mcp as a custom connector in the settings.
OpenAPI spec
4 paths, read 2026-10-28. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.