ai.useimagine/benchmark

Est-ce que ai.useimagine/benchmark est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.useimagine/benchmark » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 5 outils

• category_breakdown≈ 318 tokens

  Post counts and engagement per content category (product update, hiring, personal story, industry insight, ...) for companies or people.

  Paramètres, retour & exemple (7)

  Paramètres

  • dateTo · string · optionnel
    Inclusive end date YYYY-MM-DD (post_date).
  • source · string · optionnel · company | people | all
    'company' = the company page only, 'people' = its tracked people only, 'all' = both. Default varies per tool.
  • dateFrom · string · optionnel
    Inclusive start date YYYY-MM-DD (post_date).
  • personIds · array · optionnel
    Person UUIDs (narrows to these people).
  • companyIds · array · optionnel
    Company UUIDs. Workspace keys: omit = the live dashboard set (own company + current competitors, see the workspace tool).
  • workspaceId · string · optionnel
    Internal callers only: default the set from this workspace.
  • includeReposts · boolean · optionnel
    Include reposts. Default false.

  Exemple d'appel

  {"name": "category_breakdown", "arguments": {"dateTo": "texte", "source": "company", "dateFrom": "texte", "personIds": [], "companyIds": [], "workspaceId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• company_fit_summary≈ 343 tokens

  A company's page fit plus the distribution of its people's geometric means (median, baseline band), top people and who is under the 18-post floor. Company typical post = median over up to 5 counted fitted people plus the company page: founders, CEO and C-suite who posted in the last 90 days first, then the most active fitted people (by original posts in that window). With exactly one fitted account (a person or the page) the company ranks on that account's own fit, flagged "1 account"; it is held back while teammates still await their history pull. people.counted / countedPersonIds say who is in. Use for 'how is X doing on LinkedIn'.

  Paramètres, retour & exemple (5)

  Paramètres

  • dateTo · string · optionnel
    Inclusive end date YYYY-MM-DD (post_date).
  • company · string · optionnel
    Company name or dashboard slug, if no id.
  • dateFrom · string · optionnel
    Inclusive start date YYYY-MM-DD (post_date).
  • companyId · string · optionnel
    Company UUID. Workspace keys: omit = your own company.
  • workspaceId · string · optionnel
    Internal callers only: default to this workspace's own company.

  Exemple d'appel

  {"name": "company_fit_summary", "arguments": {"dateTo": "texte", "company": "texte", "dateFrom": "texte", "companyId": "texte", "workspaceId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• industry_landscape≈ 411 tokens

  Every account in an industry (or a custom company set): per-company rollup (page fit + people median over the 5 most active fitted people (peopleCounted), preliminary = "Few posts" under 40 team posts, solo = "1 account" when one fitted account carries the company), population vs the research baseline, and category lift with the author effect removed (which post types beat each author's own typical post). Public callers get bands and pooled lifts, the same as Discover. Use for "what works in fintech" or "where does X sit in its market".

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
    Max accounts listed, default 40, max 300.
  • dateTo · string · optionnel
    Inclusive end date YYYY-MM-DD (post_date).
  • dateFrom · string · optionnel
    Inclusive start date YYYY-MM-DD (post_date).
  • industry · string · optionnel
    Industry label, e.g. "Sales & Marketing Tech". Omit with companyIds for a custom set; omit both = the live dashboard set for workspace keys, the whole catalog for operators.
  • companyIds · array · optionnel
    Custom company set (e.g. a customer + its competitors). Workspace keys: omit (with no industry) = own company + current competitors from the dashboard.
  • workspaceId · string · optionnel
    Internal callers only: default the set from this workspace.

  Exemple d'appel

  {"name": "industry_landscape", "arguments": {"limit": 1, "dateTo": "texte", "dateFrom": "texte", "industry": "texte", "companyIds": [], "workspaceId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_companies≈ 223 tokens

  List companies in the benchmark catalog (customers, competitors, industry peers). Filter by name substring, industry, or tracking. Returns ids you pass to every other tool.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max rows, default 200, max 500.
  • query · string · optionnel
    Case-insensitive name substring, e.g. "rho".
  • industry · string · optionnel
    Exact industry label, e.g. "Sales & Marketing Tech", "AI Infrastructure", "Fintech". Omit to see all industries.
  • trackingOnly · boolean · optionnel
    Only companies in the scheduled scrapes (tracking_enabled). Default false.

  Exemple d'appel

  {"name": "list_companies", "arguments": {"limit": 1, "query": "texte", "industry": "texte", "trackingOnly": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• methodology≈ 90 tokens

  Imagine AI research rules (log-normal engagement, geometric means, research baseline 49/77/130). Call once before interpreting any numbers.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "methodology", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://benchmark.useimagine.ai/api/mcp