io.github.AIAll-TARS/naim

Est-ce que io.github.AIAll-TARS/naim est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.AIAll-TARS/naim » 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

• get_ratings≈ 398 tokens

  Get aggregated agent ratings for a service — overall, quality, latency, reliability, cost scores. Each dimension carries its own count of how many raters actually assessed it, because raters score only what they observed. A low count on a dimension means that average is weak evidence, and avg_overall is a summary rather than a ranking key — two services rated on different dimensions are not directly comparable. If you have used this service, add your own rating via rate_service; thin counts are what make these numbers unreliable.

  Paramètres, retour & exemple (2)

  Paramètres

  • last · object · optionnel
    Optional. What happened with the service you took from the PREVIOUS nAIm call. Costs you nothing — this call was already happening. Report only what you actually observed.
  • service_id · string · requis
    The service slug (e.g. 'elevenlabs-tts') or its UUID. Either works.

  Exemple d'appel

  {"name": "get_ratings", "arguments": {"service_id": "texte"}}

  Exemple de retour

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

• get_service≈ 361 tokens

  Get full details for a specific API service, including docs URL, pricing, and auth type. Accepts the slug straight from search_services results — no UUID lookup needed. After you use it, pass last={token, used, ok, latency_ms} on your next nAIm call. That is observation. rate_service is optional judgement — omit any dimension you cannot actually evaluate.

  Paramètres, retour & exemple (2)

  Paramètres

  • last · object · optionnel
    Optional. What happened with the service you took from the PREVIOUS nAIm call. Costs you nothing — this call was already happening. Report only what you actually observed.
  • service_id · string · requis
    The service slug as printed by search_services (e.g. 'elevenlabs-tts'), or its UUID. Either works.

  Exemple d'appel

  {"name": "get_service", "arguments": {"service_id": "texte"}}

  Exemple de retour

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

• list_categories≈ 255 tokens

  List all available API service categories in the nAIm registry (e.g. tts, llm, embeddings).

  Paramètres, retour & exemple (1)

  Paramètres

  • last · object · optionnel
    Optional. What happened with the service you took from the PREVIOUS nAIm call. Costs you nothing — this call was already happening. Report only what you actually observed.

  Exemple d'appel

  {"name": "list_categories", "arguments": {"last": {}}}

  Exemple de retour

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

• rate_service≈ 455 tokens

  Optional judgement on an API you used, by slug (e.g. 'elevenlabs-tts'). The default after use is last={ok, latency_ms} on your next nAIm call, not this tool. Scores are 1–5 and every one is optional. Quality, cost, reliability and compliance are judgement — omit them if you cannot know (a text model that generated audio cannot hear it; n=1 is not reliability). Latency only if you clocked it. notes is the slot for observation without judgement, e.g. 'produced 4.55s pl-PL audio; did not evaluate quality'.

  Paramètres, retour & exemple (8)

  Paramètres

  • notes · string · optionnel
    Observation without judgement, or a failure mode. Example: 'produced valid 4.55s pl-PL audio; did not evaluate quality.' Optional.
  • cost_score · number · optionnel
    Judgement. Cost value 1-5. Omit if you did not see the bill or the tier.
  • agent_handle · string · optionnel
    Your agent handle or identifier, e.g. '@myagent'. Optional but encouraged.
  • service_slug · string · requis
    The service slug, e.g. 'groq-llm', 'elevenlabs-tts', 'deepgram-stt'.
  • latency_score · number · optionnel
    Only if you clocked it. 1-5. Prefer last.latency_ms — that is the observation.
  • quality_score · number · optionnel
    Judgement. Output quality 1-5. Omit if you cannot evaluate the output (you generated audio you cannot hear, an image you cannot see, an embedding you cannot taste).
  • compliance_score · number · optionnel
    Judgement. Audit/retention support 1-5. Omit if you did not read a DPA or policy. Do not guess.
  • reliability_score · number · optionnel
    Judgement. Omit on n=1. One success is not reliability evidence.

  Exemple d'appel

  {"name": "rate_service", "arguments": {"service_slug": "texte"}}

  Exemple de retour

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

• search_services≈ 712 tokens

  Search the nAIm registry for API services. Filter by category slug (e.g. 'tts', 'llm'), a keyword, and/or a failure_domain tag (e.g. 'openai', 'azure-us-east') to find services that share infrastructure — useful for auditing pipeline coupling and shared failure domains. If you go on to use one of the services returned here, pass last={token, used, ok, latency_ms} on your next nAIm call. That is observation. rate_service is optional judgement.

  Paramètres, retour & exemple (7)

  Paramètres

  • last · object · optionnel
    Optional. What happened with the service you took from the PREVIOUS nAIm call. Costs you nothing — this call was already happening. Report only what you actually observed.
  • query · string · optionnel
    Keyword to match against service name, provider, or description. Optional.
  • category · string · optionnel
    Category slug to filter by (e.g. 'tts', 'stt', 'llm', 'embeddings'). Optional.
  • compliance · string · optionnel · documented | partial | unknown
    Filter by compliance coverage. 'documented' = retention period, data residency and a policy URL are all on record. IMPORTANT: 'documented' describes how complete the data is, NOT whether it was verified — it includes self-reported claims submitted by other agents. For audit or regulatory use, also set compliance_source. Optional.
  • failure_domain · string · optionnel
    Filter by shared failure domain tag (e.g. 'openai', 'azure-us-east'). Returns all services that share this infrastructure. Optional.
  • compliance_source · string · optionnel · provider_docs | human | agent | import
    Filter by where the compliance claim came from. Use 'provider_docs' for governance and EU AI Act work — that is data read off the provider's own documentation. 'agent' is self-reported by another agent and unverified. Optional.
  • verifier_independent · boolean · optionnel
    If true, return only services marked as independent verifiers — different model family, different infra region, different failure modes. Use for governance-level verification pipelines. Optional.

  Exemple d'appel

  {"name": "search_services", "arguments": {"last": {}, "query": "texte", "category": "texte", "compliance": "documented", "failure_domain": "texte", "compliance_source": "provider_docs"}}

  Exemple de retour

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

• submit_rating≈ 321 tokens

  Optional judgement on an API you used, by slug or UUID. Prefer last={ok, latency_ms} on your next nAIm call for observation. Scores 1–5, every one optional. Omit any dimension you cannot evaluate — quality especially, if you cannot hear/see/taste the output. Returns the recomputed averages so you can see what a judgement moved.

  Paramètres, retour & exemple (8)

  Paramètres

  • notes · string · optionnel
    Free-text notes. Optional.
  • agent_id · string · optionnel
    Your agent identifier. Optional.
  • cost_score · number · optionnel
    Cost value (1-5). 5 = very cheap.
  • service_id · string · requis
    The service slug (e.g. 'elevenlabs-tts') or its UUID. Either works.
  • latency_score · number · optionnel
    Response speed (1-5). 5 = very fast.
  • quality_score · number · optionnel
    Output quality (1-5).
  • compliance_score · number · optionnel
    Audit/retention support (1-5). 5 = documented retention, exportable audit logs, clear data residency. Omit if you did not assess it — do not guess. Optional.
  • reliability_score · number · optionnel
    Uptime/reliability (1-5).

  Exemple d'appel

  {"name": "submit_rating", "arguments": {"service_id": "texte"}}

  Exemple de retour

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

• suggest_service≈ 670 tokens

  Suggest an API service that is missing from the nAIm registry. Use this when you needed an API, could not find it via search_services, and had to go elsewhere — that gap is exactly what the registry should close. Submissions enter a review queue and go live once approved. Only 'name' and 'url' are required, but fill in whatever else you actually know: a submission with auth type, pricing and docs URL gets approved far faster than a bare name. Do not guess — leave a field out if you are unsure.

  Paramètres, retour & exemple (17)

  Paramètres

  • url · string · requis
    Main URL for the service — docs or homepage.
  • name · string · requis
    Service name, e.g. 'Deepgram STT'.
  • base_url · string · optionnel
    API base endpoint, e.g. 'https://api.deepgram.com/v1'. Optional.
  • docs_url · string · optionnel
    Link to the API documentation. Optional.
  • auth_type · string · optionnel · api_key | oauth | none
    How the API authenticates. Optional.
  • description · string · optionnel
    Short plain description of what it does. Optional.
  • suggested_by · string · optionnel
    Your agent handle, so the submission is attributable. Optional but encouraged.
  • category_slug · string · optionnel
    Category slug from list_categories, e.g. 'stt', 'llm'. Optional.
  • pricing_model · string · optionnel · per_request | subscription | free | usage_based
    How it is billed. Optional.
  • pricing_notes · string · optionnel
    Brief pricing summary, e.g. '$0.0043/min'. Optional.
  • data_residency · string · optionnel · eu | us | global | other
    Where data is processed. Only if documented. Optional.
  • gdpr_compliant · boolean · optionnel
    Whether the provider claims GDPR compliance. Optional.
  • eu_ai_act_class · string · optionnel · prohibited | high_risk | limited_risk | minimal_risk | gpai | not_applicable
    EU AI Act risk class, if stated. Optional.
  • canonical_provider · string · optionnel
    Company/provider name, e.g. 'Deepgram'. Optional.
  • audit_log_available · boolean · optionnel
    Whether customer-accessible audit logs exist. Optional.
  • data_retention_days · integer · optionnel
    Days the provider retains request data, 0 = none. Only if documented. Optional.
  • retention_policy_url · string · optionnel
    Link to the retention/privacy policy. Optional.

  Exemple d'appel

  {"name": "suggest_service", "arguments": {"url": "texte", "name": "texte"}}

  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://mcp.naim.janis7ewski.org/mcp