io.github.opennodes-io/opennodes

Est-ce que io.github.opennodes-io/opennodes est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.opennodes-io/opennodes » 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

• estimate≈ 746 tokens

  Pre-price an invocation chain BEFORE spending money. Each step is either a concrete offering ("node_id/offering_id") or a `select` query that picks the best match, plus expected input and output tokens. Returns per-step cost bounds in USD, the pinned card_revision that makes each estimate enforceable at invocation, and chain totals. Use it to compare routes or budget a multi-model pipeline; nothing is invoked or charged.

  Paramètres, retour & exemple (1)

  Paramètres

  • steps · array · requis
    Steps in execution order.

  Exemple d'appel

  {"name": "estimate", "arguments": {"steps": []}}

  Exemple de retour

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

• get_node≈ 276 tokens

  Who runs a node and how it has behaved: operator, country and regions, endpoints, declared hardware, trust tier and its history (verifications, suspensions, reinstatements, with reasons), recent registry probe results with an availability summary, and its offerings with context window and price. Use it to vet a provider before relying on it; take node_id from search_offerings, recommend or get_offering results. For one offering's full card, use get_offering.

  Paramètres, retour & exemple (2)

  Paramètres

  • node_id · string · requis
    Reverse-DNS node id, e.g. "io.opennodes.demo-node" or "import.openrouter.ai".
  • offering_limit · integer · optionnel
    Maximum offerings to list; imported catalogs can hold hundreds. `offerings_total` always gives the full count.

  Exemple d'appel

  {"name": "get_node", "arguments": {"node_id": "texte"}}

  Exemple de retour

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

• get_offering≈ 208 tokens

  Full detail for one offering: endpoints, pricing, serving capabilities (context window, supported features, languages, hardware), data policy, trust tier, and the registry's observed probe results. Take node_id and offering_id from search_offerings or recommend results.

  Paramètres, retour & exemple (2)

  Paramètres

  • node_id · string · requis
    Reverse-DNS node id, e.g. "io.opennodes.demo-node".
  • offering_id · string · requis
    Offering id within that node, as returned by search_offerings.

  Exemple d'appel

  {"name": "get_offering", "arguments": {"node_id": "texte", "offering_id": "texte"}}

  Exemple de retour

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

• recommend≈ 661 tokens

  Recommend the best AI node + model for a task, with an enforceable cost estimate and human-readable reasons. Use this first when you know the task but not the model. Pass `task` (sent to this registry, which extracts features and discards the text) or `features` already extracted on your side with extractFeatures from @opennodes/core, which keeps the prompt private. Returns ranked candidates with score components, a cost estimate pinned to the node's card revision, an optional cheaper two-step scenario, and MCP tool categories the task likely needs. To browse instead, use search_offerings; to price a specific chain, use estimate.

  Paramètres, retour & exemple (4)

  Paramètres

  • task · string · optionnel
    The task description or the prompt itself. Sent to the registry for feature extraction; use `features` to keep it private. Give this or `features`.
  • policy · object · optionnel
    Optional constraints and preferences for the recommendation.
  • features · object · optionnel
    Features from extractFeatures(prompt) in @opennodes/core: task class, size, language and needs, no prompt text. Give this or `task`.
  • est_output_tokens · integer · optionnel
    Expected answer length in tokens, if known. Improves the cost estimate; otherwise inferred from the task.

  Exemple d'appel

  {"name": "recommend", "arguments": {"task": "texte", "policy": {}, "features": {}, "est_output_tokens": 1}}

  Exemple de retour

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

• search_offerings≈ 660 tokens

  Search AI inference offerings in the OpenNodes registry — registered nodes AND imported catalogs (OpenRouter, Hugging Face Inference Providers, models.dev, local nodes). All filters are optional and combine with AND. Returns { offerings, total }: each offering has node_id, offering_id, model, pricing (USD per MTok), trust tier, serving capabilities, measured probe results, and a rank explanation. Use get_offering for one offering's full card, recommend to let the advisor choose.

  Paramètres, retour & exemple (11)

  Paramètres

  • q · string · optionnel
    Free-text match against the model metadata, offering id, and node id, e.g. "bielik" or "coder".
  • lang · string · optionnel
    Language with minimum grade, "<iso-code>[:basic|strong|native]", e.g. "pl:strong" or "de".
  • sort · string · optionnel · rank | price | ttft | tps
    rank = registry ranking (price, trust, reliability); price = cheapest input first; ttft = fastest first token; tps = highest throughput.
  • tier · string · optionnel · unverified | community | verified | attested
    Minimum trust tier. unverified < community (passed automated checks) < verified (identity and context verified) < attested.
  • limit · integer · optionnel
    Maximum offerings to return; `total` still counts every match.
  • family · string · optionnel
    Model family or exact artifact, e.g. "llama-3.3" or "qwen3". Matches model.family or model.artifact exactly.
  • scheme · string · optionnel · free | prepaid | x402
    Payment scheme the offering must accept. "free" finds no-cost offerings.
  • modality · string · optionnel · text | image | audio | video | embedding | multimodal | agent
    What the model consumes/produces. Use "text" for chat and completion models.
  • supports · string · optionnel
    Comma-separated features the offering must all support: tool_calls, json_mode, vision, streaming. Example: "tool_calls,json_mode".
  • min_context · integer · optionnel
    Minimum context window in tokens, e.g. 32768.
  • max_input_price · number · optionnel
    Maximum input price in USD per million tokens.

  Exemple d'appel

  {"name": "search_offerings", "arguments": {"q": "texte", "lang": "texte", "sort": "rank", "tier": "unverified", "limit": 1, "family": "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://registry.opennodes.io/mcp