com.realworldapis/realworldapis

Est-ce que com.realworldapis/realworldapis est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.realworldapis/realworldapis » 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 6 outils

• compare_apis≈ 612 tokens

  Compare 2–8 already-known APIs side by side using canonical catalog fields plus capability-graph summary fields such as verified capability count, physical consequences, approval relevance and irreversibility. Use get_api for the full decision profile of one API and search_capabilities for capability-level filtering. No missing value is inferred and Unknown remains Unknown.

  Paramètres, retour & exemple (2)

  Paramètres

  • apis · array · requis
    Required list of 2–8 API slugs or names. Exact matches are preferred; unique partial matches are accepted. Unresolved identifiers are reported separately, and the call fails if fewer than two records resolve.
  • fields · array · optionnel
    Optional fields to compare. The default includes core catalog fields plus verified capability count, physical-consequence count, approval-relevant count, irreversible/high-consequence count and the decision-profile URL.

  Exemple d'appel

  {"name": "compare_apis", "arguments": {"apis": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "fields": [], "method": "texte", "records": [], "unresolved": [], "evidence_policy": "texte", "capability_graph": "texte"}}

• find_api_for_task≈ 1265 tokens

  Find the best APIs for a natural-language physical-world task. Use this for open-ended task or outcome-based recommendations; use search_apis when you already know exact filters, get_api for one known API, or compare_apis for known candidates. Returns an authoritative canonical structured_results shortlist plus a best-effort AI comparison restricted to that shortlist. The canonical engine now applies Verified/High capability evidence before ranking: explicit hard requirements expressed with terms such as must, required, no or without can exclude a candidate only when verified evidence contradicts them. Unknown evidence remains eligible and is surfaced as uncertainty. requirements.mcp, openapi and auth are translated into explicit requirements; categories and capabilities remain task-shaping hints. free_tier and min_readiness are accepted for compatibility but are not hard filters.

  Paramètres, retour & exemple (3)

  Paramètres

  • task · string · requis
    Required natural-language goal or workflow, for example 'connect to a car and predict weather on the route'. Describe the desired outcome rather than naming a specific API.
  • limit · integer · optionnel
    Backward-compatible parameter. The canonical browser-parity workflow always produces five structured candidates before the AI comparison, even when another value is supplied.
  • requirements · object · optionnel
    Optional task requirements appended before canonical ranking. categories and capabilities shape task intent. mcp=Yes, openapi=Yes and auth are expressed as hard task requirements and are evaluated against verified evidence; Unknown does not count as a confirmed contradiction and remains eligible with an uncertainty. free_tier and min_readiness are accepted for backward compatibility but are not hard filters.

  Exemple d'appel

  {"name": "find_api_for_task", "arguments": {"task": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ai": {}, "name": "texte", "task": "texte", "method": "texte", "timing_ms": {}, "ai_comparison": {}, "snapshot_date": "texte", "engine_version": "texte", "coverage_status": "texte", "effective_query": "texte", "grounding_policy": {}, "source_endpoints": {}}}

• get_api≈ 626 tokens

  Retrieve one canonical API decision profile when you already know its name or slug. The response includes the full Verified/High capability profile with execution, access, approval, reversibility, physical-consequence and evidence fields. Exact slug or exact API name is preferred; a partial identifier is accepted only when it uniquely resolves to one record.

  Paramètres, retour & exemple (1)

  Paramètres

  • identifier · string · requis
    Required API slug or API name. Exact matches are preferred; a unique case-insensitive partial slug/name match is accepted. If it is ambiguous or missing, use search_apis to find the exact identifier.

  Exemple d'appel

  {"name": "get_api", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "record": {}, "source": "texte", "evidence_policy": "texte", "capability_graph": "texte"}}

• search_apis≈ 1244 tokens

  Search the canonical registry when you already know keywords or exact requirements. All supplied filter groups combine with AND logic; array capability filters require every supplied value, and protocol fields match the exact Yes/No/Unknown status, so Unknown never satisfies Yes. Results include each API's capability_summary and direct decision-profile URL. Results are sorted by agent_readiness_score descending and then API name, with 1–20 results returned (default 10). Use search_capabilities when you need capability-level filters such as approval, physical consequence, sandbox or access friction.

  Paramètres, retour & exemple (12)

  Paramètres

  • a2a · string · optionnel · Yes | No | Unknown
    Exact A2A evidence status required for a match.
  • mcp · string · optionnel · Yes | No | Unknown
    Exact MCP evidence status required for a match.
  • x402 · string · optionnel · Yes | No | Unknown
    Exact x402 evidence status required for a match.
  • limit · integer · optionnel
    Maximum number of matching records returned. Results are sorted by readiness descending then API name. total_matches still reports the full count. No pagination is currently exposed.
  • query · string · optionnel
    Optional case-insensitive text search across API name, provider, category, description, capabilities, agent capabilities and authentication fields.
  • openapi · string · optionnel · Yes | No | Unknown
    Exact OpenAPI evidence status required for a match.
  • llms_txt · string · optionnel · Yes | No | Unknown
    Exact llms.txt evidence status required for a match.
  • categories · array · optionnel
    Exact category names. Supplying multiple category values allows a record to match any listed category; this category condition still combines with every other supplied filter group using AND logic.
  • capabilities · array · optionnel
    Capability terms that must all be present in the record's verified capabilities. Matching is case-insensitive and allows a capability string to contain the supplied term.
  • min_readiness · integer · optionnel
    Strict minimum agent-readiness score. Records below this score are excluded.
  • agent_actionable · boolean · optionnel
    When true, require agent_actionable = true. False does not exclude actionable records; omit this field unless you need the positive requirement.
  • agent_capabilities · array · optionnel
    Agent capability dimensions that must all be explicitly present on a record.

  Exemple d'appel

  {"name": "search_apis", "arguments": {"a2a": "Yes", "mcp": "Yes", "x402": "Yes", "limit": 1, "query": "texte", "openapi": "Yes"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "query": "texte", "method": "texte", "filters": {}, "results": [], "returned": 1, "total_matches": 1, "evidence_policy": "texte", "capability_graph": "texte"}}

• search_capabilities≈ 1210 tokens

  Search the canonical 770-capability Verified/High decision graph directly. Use this when the question is about what an agent can actually do and under what execution conditions: task/capability text, API, category, action type, acted-on object, human approval, physical consequence, irreversibility, sandbox, hardware dependency, access friction or setup. All supplied filter groups combine with AND logic; multiple values inside one array filter are alternatives (OR). Unknown remains Unknown and may be filtered explicitly by passing the literal value Unknown.

  Paramètres, retour & exemple (15)

  Paramètres

  • limit · integer · optionnel
    Maximum capability rows returned. total_matches reports the full match count.
  • query · string · optionnel
    Optional case-insensitive text search across API/provider/category, capability key/name, primitive/action type, object, execution fields and constraints. Search terms may match across different capability fields; all supplied terms must be present somewhere in the capability record.
  • object · string · optionnel
    Case-insensitive substring match on the object acted upon, such as smart lock, parcel or charging session.
  • sandbox · array · optionnel
    Exact sandbox/test-environment labels, including Unknown when desired.
  • api_slugs · array · optionnel
    Optional API slugs. Multiple values are OR within this filter.
  • categories · array · optionnel
    Exact category labels. Multiple values are OR within this filter.
  • primitives · array · optionnel
    Exact capability primitives such as Observe, Locate, Predict, Plan, Control or Act.
  • agent_setup · array · optionnel
    Exact agent-setup labels such as Fully self-service or Human setup required.
  • action_types · array · optionnel
    Exact action types such as Read, Search, Analyze, Route or Control.
  • actionability · array · optionnel
    Exact actionability labels such as Information only, Planning or Physical action.
  • human_approval · array · optionnel
    Exact approval labels, for example Required, Not required, Depends on action or Unknown.
  • access_friction · array · optionnel
    Exact access-friction labels such as Self-service signup, Sales contract or Hardware ecosystem.
  • hardware_dependency · array · optionnel
    Exact hardware-dependency labels.
  • physical_consequence · boolean · optionnel
    When supplied, require the exact physical-consequence boolean.
  • irreversible_high_consequence · boolean · optionnel
    When supplied, require the exact irreversible/high-consequence boolean.

  Exemple d'appel

  {"name": "search_capabilities", "arguments": {"limit": 1, "query": "texte", "object": "texte", "sandbox": [], "api_slugs": [], "categories": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "method": "texte", "source": "texte", "filters": {}, "results": [], "returned": 1, "total_matches": 1, "evidence_policy": "texte", "machine_schema_version": "texte", "capability_snapshot_date": "texte"}}

• verify_requirement≈ 666 tokens

  Verify whether one specific API can satisfy one exact requirement using the canonical Verified/High capability graph plus linked assertion evidence. Returns YES, NO, PARTIAL or UNKNOWN with matched capability, access/setup prerequisites, approval, safety, reversibility, reliability, coverage and other requested dimensions; direct provider facts remain distinct from inferred policy assertions. Unknown remains Unknown.

  Paramètres, retour & exemple (3)

  Paramètres

  • api · string · requis
    Exact API slug or API name, for example nuki-web-api or Nuki Web API.
  • location · string · optionnel
    Optional geographic coverage requirement, for example Sweden. Coverage is returned as Unknown/Partial when the normalized capability graph does not contain enough location evidence.
  • requirement · string · requis
    Specific requirement to verify, for example 'remotely unlock a smart lock without human approval'.

  Exemple d'appel

  {"name": "verify_requirement", "arguments": {"api": "texte", "requirement": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"api": {}, "reasons": [], "verdict": "YES", "evidence": [], "location": "texte", "confidence": "texte", "dimensions": [], "consequence": {}, "limitations": [], "requirement": "texte", "prerequisites": {}, "schema_version": "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.realworldapis.com/mcp