Skip to main content
Glama

insourcia

by io.insourcia
OverviewDiscussionsAdmin

search_director_companies

Read-onlyIdempotent

Mandats directs d'un dirigeant : toutes les sociétés où il exerce un mandat direct, le dirigeant étant identifie de façon non ambiguë par nom + prénom + date de naissance exacte.

C'est le pivot "personne -> sociétés", complément de search_directors (trouver la personne) et get_directors (dirigeants d'une société). Cas d'usage M&A : tracer le périmètre de sociétés d'un fondateur/dirigeant (holdings, SCI, filiales) sans confondre les homonymes.

Paramètres TOUS REQUIS : nom, prenom, date_naissance (format YYYY-MM-DD). La date de naissance est obligatoire : c'est elle qui distingue la bonne personne de ses homonymes. L'obtenir au préalable via search_directors ou get_directors (champ date_naissance).

Réponse : dirigeant { nom, prenom, date_naissance, annee_naissance } + data[] = entreprises { siren, denomination, role, ville, departement, code_ape, forme_juridique } + pagination { total, returned, limit }. Résultat vide = aucun mandat direct trouvé pour cette identité exacte (vérifier la date_naissance).

Note : ne couvre que les mandats DIRECTS de la personne physique (exclut les dirigeants remontés depuis une PM représentée, resolved_from_pm). C'est la différence de périmètre avec search_companies(dirigeant_nom/prenom/naissance), qui filtre plus large (inclut ces remontées, granularité mois) et retourne des sociétés, pas les mandats directs d'un dirigeant. Pour la structure de détention capitalistique d'une société, voir get_company_graph.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nomYesNom de famille du dirigeant (requis).
limitNoNombre de sociétés à retourner (défaut 50, max 200).
prenomYesPrénom du dirigeant (requis).
date_naissanceYesDate de naissance au format YYYY-MM-DD (requis, désambiguïse les homonymes).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
messageNo
dirigeantNo
_user_planNo
paginationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre d'entreprises à retourner (défaut 50, max 200)."New value: +"Nombre de sociétés à retourner (défaut 50, max 200)."
  2. Changed3 schema fields changed
    • changedInput schema / properties / date_naissance / description
      Previous value: -"Date de naissance au format YYYY-MM-DD (requis, desambiguise les homonymes)."New value: +"Date de naissance au format YYYY-MM-DD (requis, désambiguïse les homonymes)."
    • changedInput schema / properties / limit / description
      Previous value: -"Nombre d'entreprises a retourner (defaut 50, max 200)."New value: +"Nombre d'entreprises à retourner (défaut 50, max 200)."
    • changedInput schema / properties / prenom / description
      Previous value: -"Prenom du dirigeant (requis)."New value: +"Prénom du dirigeant (requis)."
  3. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / llm_model
      Removed value: -{
-  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "nom",
-  "prenom",
-  "date_naissance",
-  "llm_model"
-]New value: +[
+  "nom",
+  "prenom",
+  "date_naissance"
+]
  4. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "nom",
-  "prenom",
-  "date_naissance"
-]New value: +[
+  "nom",
+  "prenom",
+  "date_naissance",
+  "llm_model"
+]
  5. Changed1 schema field changed
    • changedOutput schema / properties / pagination / additionalProperties
      Previous value: -falseNew value: +{}
  6. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "nom",
-  "prenom",
-  "date_naissance",
-  "context"
-]New value: +[
+  "nom",
+  "prenom",
+  "date_naissance"
+]
  7. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "nom",
-  "prenom",
-  "date_naissance"
-]New value: +[
+  "nom",
+  "prenom",
+  "date_naissance",
+  "context"
+]
  8. First observed

TDQS

Score is being calculated.

All insourcia toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources