CalculPro — outils de calcul du bâtiment
Server Details
Calculs du bâtiment (France) : chute de tension NF C 15-100 et catalogue de 111 outils.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Available Tools
2 toolscalculer_chute_de_tensionChute de tension d'un câble (NF C 15-100)ARead-onlyIdempotentInspect
Calcule la chute de tension d'une canalisation électrique basse tension et la confronte aux limites de la NF C 15-100 § 525, par la méthode du guide UTE C 15-105.
Deux usages selon que la section est connue :
vérification — donnez
section, l'outil rend un verdict de conformité ;dimensionnement — omettez
section, l'outil retient la plus petite section normalisée qui tient la limite.
Renvoie aussi la longueur maximale admissible, la tension à l'arrivée, les pertes Joule et la chute obtenue pour chaque section normalisée.
Domaine de validité : une canalisation à section constante, en régime établi et charge équilibrée, conducteurs cuivre ou aluminium, réactance forfaitaire de 0,08 mΩ/m. L'outil ne vérifie NI le courant admissible du câble (échauffement, mode de pose, facteurs de correction), NI la protection contre les contacts indirects, NI le pouvoir de coupure des protections. La chute de tension n'est qu'un critère parmi d'autres : une section validée ici reste à vérifier en courant admissible avant d'être retenue.
| Name | Required | Description | Default |
|---|---|---|---|
| usage | No | « eclairage » pour un circuit d'éclairage, limite plus sévère ; « autre » pour prises, force et moteurs (défaut). | |
| reseau | No | Type de réseau : « mono » phase + neutre, « tri » triphasé (défaut), « dc » courant continu. | |
| cos_phi | No | Facteur de puissance du récepteur (défaut 0,85). Sans effet en courant continu. | |
| courant | No | Courant d'emploi IB, en ampères. Renseignez soit le courant, soit la puissance. | |
| section | No | Section d'un conducteur, en mm². Omettez ce champ quand l'utilisateur cherche quelle section poser : l'outil bascule alors en dimensionnement. | |
| tension | No | Tension nominale, en volts — entre phases en triphasé. Défauts : 230 V en monophasé, 400 V en triphasé, 48 V en continu. | |
| longueur | Yes | Longueur simple de la canalisation, en mètres. Donnez la distance aller seulement : le trajet retour est déjà pris en compte. | |
| materiau | No | Métal du conducteur (défaut : cuivre). | |
| puissance | No | Puissance active transportée, en kW. Alternative au courant d'emploi. | |
| chute_amont | No | Chute de tension déjà consommée en amont, en %, pour chaîner plusieurs tronçons (défaut 0). | |
| alimentation | No | Origine de l'installation. « reseau-bt » : branchement au réseau public basse tension, limites 3 % en éclairage et 5 % pour les autres usages — c'est le défaut, à la fois le cas le plus courant et le plus sévère. « poste-prive » : poste de livraison HTA/BT privé, limites 6 % et 8 %. | |
| rapport_id_in | No | Rapport courant de démarrage sur courant nominal du moteur (défaut 6 ; typiquement 5 à 8). | |
| moteur_demarrage | No | Vérifier en plus la chute au démarrage d'un moteur asynchrone, sous cos φ 0,35 et une limite usuelle de 15 %. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and idempotent. The descrption goes well beyond that by disclosing the calculation method (UTE C 15-105), core assumptions (constant section, steady state, balanced load, fixed reactance 0.08 mΩ/m), and the practical caveat that a validated section still requires verification of current-carrying capacity. This gives the agent a clear behavioral model of the computation without any contradiction.
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 description is compact despite covering a complex tool. It front-loads the purpose, then uses clear structured bullets for the two modes, the returned values, and the validity domain. Every sentence carries information needed for correct invokation; no filler or redundancy is present.
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 compensates by explicitly listing the returned quantities (maximum admissible length, arrival voltage, Joule losses, voltage drop per normalized section). It also covers domain limits, input-mode switching, and important exclusions. For a tool with 13 parameters and significant calculation subtleties, this description is complete enough for an agent to select and call it correctly.
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 the baseline is 3. The description reinforces key usage semantics—such as omitting `section` to trigger sizing and renseigning either `courant` or `puissance`—but it does not add substantial parameter-specific detail beyond what the schema already documents. The added value is mostly contextual rather than per-parameter.
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 description opens with a specific verb and resource: 'Calcule la chute de tension d'une canalisation électrique basse tension' and identifies the governing standard (NF C 15-100 § 525). It further distinguishes the two operational modes—verification when a section is provided and sizing when it is omitted—so an agent understands exactly what the tool performs and how it differs from its only sibling, rechercher_outil.
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?
The description gives explicit when-to-use guidance: provide `section` for verification, omit it for sizing. It also clearly states the domain of validity and, crucially, enumerates what the tool does NOT check (current-carrying capacity, indirect contact protection, breaking capacity), thereby guiding the agent away from misusing it as a complete cable-sizing decision tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
rechercher_outilRechercher un outil CalculProARead-onlyIdempotentInspect
Recherche un outil de calcul dans le catalogue CalculPro (111 outils : chauffage, plomberie, ventilation, électricité, structure et Eurocodes, isolation, acoustique, éclairage, menuiserie, accessibilité, gaz…).
À appeler quand la demande relève d'un calcul du bâtiment qu'aucun autre outil de ce serveur ne couvre. Renvoie les outils pertinents avec leur adresse, pour orienter l'utilisateur vers le calcul complet sur calculpro.fr.
Cet outil ne calcule rien : il ne fait que chercher dans le catalogue.
| Name | Required | Description | Default |
|---|---|---|---|
| limite | No | Nombre maximum d'outils à renvoyer (défaut 8). | |
| requete | Yes | Ce que l'utilisateur cherche à calculer, en français — par exemple « déperditions thermiques », « section de câble », « débit d'eau », « poutre acier ». |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
La description complète les annotations readOnly et idempotent en déclairant le comportement réel : l'outil ne calcule pas, il renvoie des outils pertinents avec leur adresse pour rediriger vers calculpro.fr. Cette transparence est utile car il n'y a pas de schéma de sortie.
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?
La description est bien structurée en trois phraces : but, condition d'usage, et limitation. Elle est dense et informative sans remplissage, et l'information la plus importante est mise en tête.
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?
Pour un outil de recherche simple avec deux paramètres, des annotations riches et aucun schéma de sortie, la description couvre l'essentiel : périmètre, moment d'usage, retour attendu et comportement négatif. Rien de nécessaire manque pour que l'agent invoque correctement l'outil.
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?
Le schéma d'entrée couvre déjà 100% des paramètres avec des descriptions claires pour 'requête' et 'limite', incluant exemples et valeur par défaut. La description de l'outil n'ajoute pas d'information paramétrique supplémentaire, donc le score de base de 3 est approprié.
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?
La description utilise un verbe d'action précis et nomme la ressource : 'Recherche un outil de calcul dans le catalogue CalculPro'. Elle énumère les domaines couverts et précise explicitement 'Cet outil ne calcule rien : il ne fait que chercher dans le catalogue', ce qui le distingue clairement du outil frère calculer_chute_de_tension.
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?
La condition d'usage est explicite : 'À appeler quand la demande relève d'un calcul du bâtiment qu'aucun autre outil de ce serveur ne couvre'. Cela oriente l'agent vers cet outil si la demande n'est pas déjà couverte par un outil de calcul, ce qui lève toute ambiguïté avec le sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Frequently Asked Questions
Claiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as
io.github.alice/server, link the matching GitHub user or an account that owns the GitHub organization, then choose Claim with GitHub.HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at
/.well-known/glama.jsonon the same origin as the connector, then choose Check HTTP challenge.DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Related MCP Connectors
Cálculos de engenharia elétrica pela norma brasileira (NBR), validados, com citação normativa.
27 engineering compliance and calculation tools for the built environment (UK, EU, UAE).
Calculatrices francaises : salaire net, SMIC, impots, bareme kilometrique, TVA, conversions.
Draw buildings as DXF, IFC and 3D, plus exact French rent and charges calculations.
Related MCP Servers
- AlicenseAqualityAmaintenanceConstruction trade compliance MCP server. Covers electrical, plumbing, HVAC, welding, roofing, gas fitting, solar and more across Australia, UK, USA, Canada and EU. 8 tools (3 free, 5 pro): compliance checking, cable sizing, RAMS generation, safety checklists, material compliance verification and inspection requirements. Works in Claude Desktop, Cursor, Windsurf and any MCP client.8481MIT
- AlicenseAqualityCmaintenanceThe most comprehensive everyday calculator MCP server — 501 tools across 22 categories covering 8 countries' tax systems (FR, BE, CH, CA, US, UK, MA, SN). Finance, health, math, science, construction, conversions, education, sport, cooking, travel, and more. Free, no API key required. Streamable HTTP transport.15191MIT
- AlicenseCqualityCmaintenance27 deterministic engineering compliance and calculation tools for the built environment (data-centre PUE and EED, EPBD, NIS2, Eurocode, UAE compliance), callable by AI agents via MCP and REST API. Free tier; every result cites the governing standard.27MIT
- FlicenseNot gradedqualityBmaintenanceProvides electrical pricing, cable sizing, and profitability analysis tools for construction estimating, integrating with Claude to answer pricing queries based on a US-market-calibrated price list and NEC standards.5
Glama MCP Gateway
Add one secure layer between your agents and this server.
TDQS
Les deux outils sont parfaitement distincts : l'un effectue un calcul technique précis, l'autre ne fait que rechercher dans un catalogue. Aucun risque de confusion entre leurs fonctions.
Les deux noms suivent le même schéma verbe_nom en minuscules avec underscores : calculer_chute_de_tension et rechercher_outil. La convention est cohérente.
Avec seulement deux outils pour un domaine annoncé aussi vaste que le calcul du bâtiment, l'ensemble semble mince. L'outil de recherche compense partiellement en orientant vers 111 outils externes, mais le serveur lui-même reste très limité en nombre.
Le serveur ne propose qu'un seul vrai calcul (chute de tension) alors que son domaine couvre chauffage, plomberie, ventilation, structure, etc. L'outil de recherche ne calcule rien et renvoie vers un site externe, ce qui laisse des lacunes importantes pour un agent qui deverait effectuer d'autres calculs directement.