Skip to content
Apparais logo

Apparais MCP server

Which MCP servers are Apparais'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 2026-11-04

← Back to Apparais

Whose server it is
  • Registry namefr.apparais.www/apparaisverified in the MCP registry

The registry name sits under apparais.fr. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-04
  • Stateanswerschecked 2026-11-04
  • Tools4
  • Server calls itselfapparais
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 644 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

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.

Measured dailydaily checks: 1, the first on 2026-11-04
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer823 ms
  • Space in an agent's context≈ 433 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 →

Tools it offers4 tools · read 2026-11-04
  • classement_chatgpt

    Renvoie les commerces que ChatGPT recommande le plus pour un métier dans une ville française (classement Apparais, mis à jour régulièrement), avec la part des réponses où chacun est cité et les sites que ChatGPT consulte.

  • liste_classements

    Liste les classements Apparais déjà publiés (métier × ville), filtrables par ville ou par métier.

  • tester_mon_commerce

    Donne le lien du test gratuit Apparais pour un commerce précis : score ChatGPT sur 10 questions de clients, concurrents qui passent devant, score de la fiche Google. Résultat en ~30 secondes, sans carte bancaire.

  • checklist_visibilite_locale

    Checklist concrète et priorisée pour qu'un commerce local soit recommandé sur Google Maps et par ChatGPT (fiche Google, avis, annuaires, site, données structurées).

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "apparais": {
      "type": "http",
      "url": "https://www.apparais.fr/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http apparais https://www.apparais.fr/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.apparais.fr/mcp as a custom connector in the settings.

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.