Skip to main content
Glama
fauguste

boondmanager-mcp-server

by fauguste

Rechercher des projets

boond_projects_search
Read-onlyIdempotent

Search projects in BoondManager with server-side filters for periods, states, types, client companies, managers, and more. Get paginated results to find projects by your criteria.

Instructions

Recherche des projets / missions dans BoondManager avec filtres serveur.

Cas d'usage courants : • Mes projets sans connaître son propre ID : perimeterDynamic: ["data"]. Pour "projets de X" : perimeterManagers: [<X_id>]. • États / types : projectStates: [<id>] (dictionnaire setting.state.project), projectTypes: [<id>] (setting.typeOf.project). IDs entiers. • Société cliente : companies: [<companyId>] (filtre les projets rattachés à ces sociétés). • Lié à un contact / opportunité / contrat / ressource / produit : utiliser keywords avec préfixes — "PRJ<id>" (projet), "CSOC<id>" (société), "CCON<id>" (contact), "AO<id>" (opportunité), "CTR<id>" (contrat), "COMP<id>" (ressource), "PROD<id>" (produit), "MIS<id>" (livraison). • Métier : activityAreas, expertiseAreas, flags (tags). • Période : period: "running" (en cours), "created", "started", "stopped", "closed", "updated", "hasAdditionalDataOrPurchase" + startDate/endDate. Ex: projets en cours en 2026 → period: "running", startDate: "2026-01-01", endDate: "2026-12-31".

Tri : sort: "startDate"|"endDate"|"reference"|"company.name"|"mainManager.lastName" + order.

Returns : liste paginée des projets. Utiliser boond_projects_get ou les outils d'onglets pour le détail.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoNuméro de page (défaut: 1, max: 100)
sortNoChamp de tri (ex: lastName, firstName, updateDate)
flagsNoIDs de tags.
orderNoOrdre de tri (asc/desc)
fieldsNoProjection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.
periodNoFiltre temporel : 'running' (en cours), 'created', 'started', 'stopped', 'closed', 'updated', 'hasAdditionalDataOrPurchase'. À combiner avec `startDate` + `endDate`.
endDateNoDate de fin (YYYY-MM-DD), à utiliser avec `period`.
keywordsNoMots-clés. Pour cibler par ID préfixé : 'PRJnnn' (projet), 'CSOCnnn' (société), 'CCONnnn' (contact), 'AOnnn' (opportunité), 'COMPnnn' (ressource), 'CTRnnn' (contrat).
pageSizeNoNombre de résultats par page (max: 500, défaut: 30)
companiesNoIDs de sociétés clientes : projets rattachés à ces sociétés.
startDateNoDate de début (YYYY-MM-DD), à utiliser avec `period`.
projectTypesNoIDs de types de projet (dictionnaire setting.typeOf.project).
activityAreasNoIDs de secteurs d'activité.
projectStatesNoIDs d'états de projet (dictionnaire setting.state.project).
expertiseAreasNoIDs de domaines d'expertise.
perimeterPolesNoIDs de pôles. Conserve les entités dont le responsable appartient à ces pôles.
narrowPerimeterNoSi true, jointure ET entre les filtres `perimeter*` (au lieu de OU par défaut).
perimeterDynamicNoPérimètre dynamique relatif à l'utilisateur courant (raccourci sans avoir à connaître son propre ID). Valeurs : 'data' (mes propres données), 'managers' (mon équipe / mes N-1), 'agencies' (mes agences), 'poles' (mes pôles), 'businessUnits' (mes BU). Combinable.
perimeterAgenciesNoIDs d'agences. Conserve les entités dont le responsable appartient à ces agences.
perimeterManagersNoIDs des managers (ressources). Conserve les entités dont le responsable est l'un de ces managers. Pour 'mon équipe / N-1 d'une personne X', passer [X_id]. Obtenir son propre ID via boond_application_current_user.
perimeterBusinessUnitsNoIDs de business units. Conserve les entités dont le responsable appartient à ces BU.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNombre d'éléments retournés sur cette page
itemsYes
totalNoNombre total de résultats côté BoondManager
Install Server

TDQS

A5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent hints, the description reveals that filtering is done server-side and the result is a paginated list of projects. It also clarifies that this tool provides only summaries, not details, directing to complementary tools for richer data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured with bullet points, starting with a one-line summary and then grouping filters by use case. It is detailed but not repetitive, with each bullet providing actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the large number of optional parameters (21) and an output schema, the description covers the most common search scenarios, sorting options, and pagination, while leaving the rest to the schema. It also mentions the existence of other tools for detail, making it complete for an AI agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the description still adds value by giving scenario-based explanations, e.g., `period: "running"` plus `startDate`/`endDate` for projects running in 2026, and expands the keyword prefix list (including `PROD` and `MIS`) beyond the schema's set. Also clarifies that `perimeterDynamic: ["data"]` does not require knowing one's own ID.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Recherche des projets / missions dans BoondManager avec filtres serveur', clearly stating the verb (rechercher), resource (projets/missions), and server-side filtering. It distinguishes from sibling search tools by focusing on projects and explicitly redirects to boond_projects_get for detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides common usage patterns ('Cas d'usage courants') with concrete parameter examples, such as `perimeterDynamic: ["data"]` for one's own projects and `perimeterManagers: [<X_id>]` for a specific manager's projects. It also states 'Utiliser boond_projects_get ou les outils d'onglets pour le détail' to delineate when to use this search vs detail tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fauguste/boondmanager-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server