
Meridal MCP server
Which MCP servers are Meridal'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 2026-10-27
- Registry namefr.meridal/relevesverified in the MCP registry
The registry name sits under meridal.fr. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools5
- Server calls itselffr.meridal/releves
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 722 ms.
- Whether its tools do the product's job has not been judged yet.
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 answer861 ms
- Space in an agent's context≈ 759 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
- cannot · automate copying the same data between software tools
- not sure · give staff a shared AI assistant that follows company methods
- not sure · draw up a written plan of tasks suited to tools
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 →
prix_du_modeleCherche un modèle de langage par nom, identifiant d'API ou fournisseur, et rend son prix par million de tokens (entrée, sortie, entrée en cache, en dollars), sa fenêtre de contexte, sa licence, ses données d'hébergement en Europe et ses…
comparer_les_abonnementsRend les abonnements d'équipe et d'entreprise (prix par utilisateur et par mois, engagement, nombre de sièges, ce qui est compris, entraînement sur les données, résidence des données en Europe) et, pour Microsoft, Google, Anthropic…
classement_d_un_testRend les notes des modèles à un test (Artificial Analysis, GPQA, SWE-bench, Arena…), de la plus haute à la plus basse, chaque note avec sa source, son adresse et sa date, et le test avec ce qu'il mesure et ses limites connues. Sans test…
reglage_d_un_outilCherche un réglage dans les consoles d'administration des éditeurs (Microsoft 365, Claude, ChatGPT, Gemini, Mistral…) et rend son chemin en français et en anglais, le rôle qui peut le changer, sa valeur par défaut, et la page d'aide de…
date_des_relevesRend la date de chaque relevé, l'adresse de ses fichiers (JSON, CSV) et de la page qui les décrit, et le calendrier réglementaire (dates d'application de la réglementation sur l'IA). À appeler avant de citer un prix : un prix se lit à sa…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"releves": {
"type": "http",
"url": "https://meridal.fr/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http meridal https://meridal.fr/mcpclaude.ai, ChatGPT and other clients: add https://meridal.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.
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.