Combien d'outils expose ai.objekts.mcp/production-desk ?

ai.objekts.mcp/production-desk expose 7 outil(s). Le coût de contexte pour les charger tous est d'environ 6388 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Communication / ai.objekts.mcp/production-desk

ai.objekts.mcp/production-desk

serveur MCP (Model Context Protocol) · objekts-production-desk 0.1.0

▸ Communication

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~6388 tokensCoût de contexte

7Outils

Est-ce que ai.objekts.mcp/production-desk est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.objekts.mcp/production-desk » 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 7 outils

create_upload_session≈ 300 tokens
Use this only when the user explicitly wants an original production file delivered to objekts and the current host cannot pass that original file natively. It creates a short-lived private upload URL. Do not use it merely to analyze files that are already available in the conversation.
Paramètres, retour & exemple (4)
Paramètres
- filename · string · requis
- confirmed · boolean · requis
- mediaType · string · requis
- sizeBytes · integer · requis
Exemple d'appel
```
{"name": "create_upload_session", "arguments": {"filename": "texte", "confirmed": true, "mediaType": "texte", "sizeBytes": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"uploadId": "texte", "expiresAt": "texte", "uploadUrl": "texte"}}
```
delete_production_brief≈ 208 tokens
Use this only when the user explicitly asks to delete a production submission from objekts storage. This removes the stored submission record and is destructive.
Paramètres, retour & exemple (2)
Paramètres
- confirmed · boolean · requis
- submissionId · string · requis
Exemple d'appel
```
{"name": "delete_production_brief", "arguments": {"confirmed": true, "submissionId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"deleted": true}}
```
diagnose_production≈ 2338 tokens
Use the objekts Production Desk production-diagnosis engine for production-heavy visual work before proposing execution. It checks reference authority, hard locks, truth-layer routing, asset fitness, continuity, versioning, revision impact, readiness and the highest-value proof-of-concept. It does not estimate price, collect contact data, upload files or send anything externally. Populate only facts available from the user's current request/files; mark unknowns explicitly instead of inventing production facts. After the call, use visibleVerdict as the complete default answer: do not add a generic checklist or extra recommendations unless the user explicitly asks for a broader audit.
Paramètres, retour & exemple (8)
Paramètres
- assets · array · optionnel
- changes · array · optionnel
- unknowns · array · optionnel
- versions · array · optionnel
- objective · string · requis
- readiness · object · requis
- deliverables · array · requis
- elementRoutes · array · optionnel
Exemple d'appel
```
{"name": "diagnose_production", "arguments": {"objective": "texte", "readiness": {}, "deliverables": []}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"visibleVerdict": {}, "responseContract": {}}}
```
estimate_production≈ 2574 tokens
Return a directional RUB production range and timeline only when the user explicitly asks about price, cost, budget, quote, or budget fit. This tool is read-only, non-binding, and never collects contact details or submits a brief. Choose WHOLE_PRODUCTION for a finished deliverable and BOUNDED_SHOT_POST for named shots/scenes/post work; use INFERRED when that scope is genuinely ambiguous, or SCENARIO for a clearly labeled hypothetical. For production diagnosis without pricing, use diagnose_production instead.
Paramètres, retour & exemple (15)
Paramètres
- mode · string · requis · ROM | SCOPED_ESTIMATE | BUDGET_FIT | DEADLINE_FIT
  ROM for an early range; SCOPED_ESTIMATE for a defined scope; BUDGET_FIT to compare scope with a target budget; DEADLINE_FIT to evaluate schedule pressure.
- units · array · requis
  Production line items that drive the estimate. Include every material discipline/unit being priced; each item explains quantity, complexity, locks, continuity, and basis.
- scopeType · string · requis · WHOLE_PRODUCTION | BOUNDED_SHOT_POST
  WHOLE_PRODUCTION prices the complete requested finished deliverable; BOUNDED_SHOT_POST prices only named shots, scenes, VFX, or post tasks.
- exclusions · array · optionnel
  Work explicitly outside this estimate, especially live-action, rights, media, extra versions, or unrequested disciplines.
- scopeBasis · string · requis
  One concise sentence stating exactly what the estimate includes and excludes from the priced object.
- versioning · object · optionnel
  Version/adaptation workload beyond the master deliverable; distinguish simple exports from recomposition and new production.
- assumptions · array · optionnel
  Explicit factual assumptions used to make the estimate possible; do not invent client facts.
- deadlineDays · ? · optionnel
  Calendar days available until delivery when known; null or omit when no deadline is supplied.
- scopeDecision · string · requis · USER_EXPLICIT | SCENARIO | INFERRED
  USER_EXPLICIT when the requested object is clear; SCENARIO for an explicitly labeled hypothetical; INFERRED only when scope is genuinely ambiguous, in which case no price is returned until clarified.
- scopeEvidence · string · requis
  Short evidence for the scope choice. For USER_EXPLICIT, copy a brief verbatim phrase from the user's request that identifies the priced object.
- runtimeSeconds · ? · requis
  Final master runtime in seconds when known; null only when genuinely unknown.
- targetBudgetMax · ? · optionnel
  Upper bound of the user's target budget in RUB for BUDGET_FIT; omit when no target ceiling is supplied.
- targetBudgetMin · ? · optionnel
  Lower bound of the user's target budget in RUB for BUDGET_FIT; omit when no budget floor exists.
- externalBidItems · array · optionnel
  Known cost exposures that require third-party bids; these remain outside the automated production range.
- includeDepartments · array · optionnel
  Optional whitelist of departments to include when the requested estimate intentionally covers only selected disciplines.
Exemple d'appel
```
{"name": "estimate_production", "arguments": {"mode": "ROM", "units": [], "scopeType": "WHOLE_PRODUCTION", "scopeBasis": "texte", "scopeDecision": "USER_EXPLICIT", "scopeEvidence": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "ROM", "currency": "texte", "rangeMax": 1, "rangeMin": 1, "budgetFit": {}, "scopeType": "WHOLE_PRODUCTION", "confidence": "LOW", "exclusions": [], "scopeBasis": "texte", "assumptions": [], "costDrivers": [], "departments": []}}
```
get_production_brief_status≈ 304 tokens
Use this when the user wants the current human-review status, producer questions or available human estimate for a production brief previously submitted to objekts. It does not modify the submission.
Paramètres, retour & exemple (1)
Paramètres
- submissionId · string · requis
Exemple d'appel
```
{"name": "get_production_brief_status", "arguments": {"submissionId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "RECEIVED", "message": "texte", "questions": [], "submissionId": "texte", "humanEstimate": "texte"}}
```
submit_production_brief≈ 568 tokens
Use this only after the user explicitly confirms that the prepared production brief, one reply channel (email or Telegram), and selected files should be sent to objekts for human production review. A contactless human-review submission is not allowed because the producer must be able to answer the user. When the host already has the files, pass them through the files field instead of making the user upload them again. Do not use it for local analysis, estimation, or when the user has said not to send anything.
Paramètres, retour & exemple (5)
Paramètres
- brief · object · requis
- files · array · optionnel
- contact · object · requis
- confirmed · boolean · requis
- selectedAssetIds · array · optionnel
Exemple d'appel
```
{"name": "submit_production_brief", "arguments": {"brief": {}, "contact": {}, "confirmed": true}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "message": "texte", "submissionId": "texte"}}
```
update_production_brief≈ 542 tokens
Use this only after the user explicitly confirms that clarifications, scope updates, newly supplied asset references or attached production files should be sent to an existing objekts human review. When ChatGPT already has a requested file, pass it through the files field rather than creating a second upload. Do not use it to change a brief that exists only in the current conversation.
Paramètres, retour & exemple (6)
Paramètres
- files · array · optionnel
- answers · object · optionnel
- confirmed · boolean · requis
- briefPatch · object · optionnel
- submissionId · string · requis
- addedAssetIds · array · optionnel
Exemple d'appel
```
{"name": "update_production_brief", "arguments": {"confirmed": true, "submissionId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "RECEIVED", "message": "texte", "questions": [], "submissionId": "texte", "humanEstimate": "texte"}}
```

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://mcp.objekts.ai/mcp