accueil / serveurs / IA & Mémoire / com.claude-world/worlds-knowledge
com.claude-world/worlds-knowledge
serveur MCP (Model Context Protocol) · worlds-knowledge-mcp-server 0.5.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que com.claude-world/worlds-knowledge est sûr ?
Au dernier audit MCP Hub, le serveur MCP « com.claude-world/worlds-knowledge » 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 12 outils
- worlds_advise_hard_problem≈ 2250 tokens
Choose the maximum-depth model-and-effort pairing for one difficult problem within the caller's actual CLI set. For a single CLI it selects that provider's strongest catalog role; with multiple CLIs it returns provider candidates but does not invent a universal cross-provider winner. It uses single-task depth, never ultra or ultracode orchestration, defaults to read-only, and does not launch a CLI or grant permissions.
Paramètres, retour & exemple (6)
Paramètrestask· string · requiscurrent_cli· string · requis · claude-code | codex | grok-buildpreferred_cli· string · optionnel · claude-code | codex | grok-build
Optional user-selected provider. This is an explicit preference, not a benchmark verdict.available_clis· array · optionnelselection_scope· string · optionnel · current-cli | available-clisexecution_intent· string · optionnel · read-only | may-edit
Exemple d'appel{"name": "worlds_advise_hard_problem", "arguments": {"task": "texte", "current_cli": "claude-code"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"task": "texte", "safety": {}, "evidence": [], "current_cli": "claude-code", "decision_rule": "texte", "recommendation": {}, "advisor_version": "texte", "selection_scope": "current-cli", "provider_candidates": [], "live_validation_steps": [], "cross_provider_verdict": "texte"}} - worlds_compare_cli_workflows≈ 864 tokens
Find evidence for the same task across Claude Code, Codex, and Grok Build without pretending their commands or authority models are identical. Returns separately ranked groups with source dates and canonical links. Best for questions such as configuring MCP, repository instructions, approvals, subagents, or headless CI.
Paramètres, retour & exemple (4)
Paramètresquery· string · requislanguage· string · optionnel · en | zh-tw | japroducts· array · optionnellimit_per_product· integer · optionnel
Exemple d'appel{"name": "worlds_compare_cli_workflows", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "groups": [], "language": "en"}} - worlds_get_cli_command≈ 875 tokens
Return one current command path with all captured flags, arguments, value shapes, availability, risk, release metadata, and official source links. Accepts a stable id or full command path.
Paramètres, retour & exemple (2)
Paramètrescommand· string · requisproduct· string · requis · claude-code | codex | grok-build
Exemple d'appel{"name": "worlds_get_cli_command", "arguments": {"command": "texte", "product": "claude-code"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"command": {}, "product": "claude-code", "release": {}, "sources": [], "display_name": "texte", "reference_url": "texte"}} - worlds_get_cli_configuration≈ 747 tokens
Search configuration keys and environment-variable names for one CLI. Returns public schema metadata and source links, never local values.
Paramètres, retour & exemple (6)
Paramètreslimit· integer · optionnelquery· string · optionneloffset· integer · optionnelinclude· string · optionnel · config | environment | bothproduct· string · requis · claude-code | codex | grok-buildavailability· array · optionnel
Exemple d'appel{"name": "worlds_get_cli_configuration", "arguments": {"product": "claude-code"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "items": [], "query": "texte", "total": 1, "offset": 1, "product": "claude-code", "has_more": true, "next_offset": 1, "reference_url": "texte", "release_version": "texte"}} - worlds_get_cli_workflow≈ 1118 tokens
Find one provider-specific workflow and its recorded command steps without translating flags between providers.
Paramètres, retour & exemple (2)
Paramètresproduct· string · requis · claude-code | codex | grok-buildworkflow· string · requis
Exemple d'appel{"name": "worlds_get_cli_workflow", "arguments": {"product": "claude-code", "workflow": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"product": "claude-code", "sources": [], "commands": [], "workflow": {}, "guide_url": "texte", "reference_url": "texte", "release_version": "texte", "interactive_commands": []}} - worlds_get_document≈ 528 tokens
Read the bounded public excerpt and metadata for one source-checked CLI manual returned by worlds_search_knowledge. Follow canonical_url for the complete manual. Structured CLI command tools remain complete.
Paramètres, retour & exemple (3)
Paramètresid· string · requis
Stable document id from a search or comparison result.offset· integer · optionnelmax_characters· integer · optionnel
Exemple d'appel{"name": "worlds_get_document", "arguments": {"id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "title": "texte", "world": "claude", "product": "claude-code", "summary": "texte", "language": "en", "reviewed_at": "texte", "content_type": "texte", "published_at": "texte", "rights_basis": "texte", "canonical_url": "texte", "fixed_excerpt": "texte"}} - worlds_list_catalog≈ 333 tokens
Return public corpus counts, supported worlds, languages, products, source-quality counts, the build commit, and the current publication gate. This public DTO deliberately excludes local paths, package names, and private repository URLs.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "worlds_list_catalog", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"worlds": [], "released_at": "texte", "generated_at": "texte", "content_policy": "texte", "schema_version": 1, "dataset_version": "texte", "total_documents": 1}} - worlds_list_cli_models≈ 1084 tokens
Return dated, source-grounded model catalogs for Claude Code, Codex, and Grok Build, including selector syntax, per-model effort support, availability constraints, and provider-native orchestration modes. These are snapshots; verify the live account catalog before launch.
Paramètres, retour & exemple (1)
Paramètresproducts· array · optionnel
Exemple d'appel{"name": "worlds_list_cli_models", "arguments": {"products": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"warning": "texte", "catalogs": [], "freshness": {}, "catalog_version": "texte"}} - worlds_list_cli_versions≈ 874 tokens
Return the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for all three CLIs.
Paramètres, retour & exemple (1)
Paramètresproducts· array · optionnel
Exemple d'appel{"name": "worlds_list_cli_versions", "arguments": {"products": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"products": [], "generated_at": "texte", "rights_basis": "texte", "schema_version": 1}} - worlds_plan_cli_work≈ 1878 tokens
Create a read-only, dependency-aware work plan across Claude Code, Codex, and Grok Build. It selects a concrete dated-catalog model and supported native effort for each workstream, while keeping CLI fit, orchestration, permissions, handoff context, and verification separate. Routing is continuity-first and does not claim benchmark superiority, launch another CLI, or enable permission bypass.
Paramètres, retour & exemple (10)
Paramètrestask· string · requisstrategy· string · optionnel · continuity-first | quality-first | speed-first | cost-firstcurrent_cli· string · requis · claude-code | codex | grok-build
CLI holding the active conversation; continuity is preferred unless switching has a concrete benefit.workstreams· array · optionnelavailable_clis· array · optionnelrisk_tolerance· string · optionnel · low | medium | highorchestration_mode· string · optionnel · none | provider-native-if-supportedmax_parallel_tracks· integer · optionnelexecution_environment· string · optionnel · local-workspace | ci-runner | externally-sandboxed-runnerrequire_independent_review· boolean · optionnel
Exemple d'appel{"name": "worlds_plan_cli_work", "arguments": {"task": "texte", "current_cli": "claude-code"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"task": "texte", "safety": {}, "handoff": {}, "evidence": [], "strategy": "continuity-first", "assignments": [], "current_cli": "claude-code", "routing_basis": "texte", "uncertainties": [], "available_clis": [], "planner_version": "texte", "routing_principles": []}} - worlds_search_cli_reference≈ 808 tokens
Search current command paths, flags, interactive commands, configuration names, environment-variable names, workflows, and release drift for Claude Code, Codex, and Grok Build. Results contain factual metadata and official source links.
Paramètres, retour & exemple (6)
Paramètreskinds· array · optionnellimit· integer · optionnelquery· string · requisoffset· integer · optionnelproducts· array · optionnelavailability· array · optionnel
Exemple d'appel{"name": "worlds_search_cli_reference", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "items": [], "query": "texte", "total": 1, "offset": 1, "has_more": true, "next_offset": 1}} - worlds_search_knowledge≈ 1115 tokens
Search 162 multilingual, source-checked operating manuals for Claude Code, Codex, and Grok Build: 18 CLI usage and feature modules per product in English, Traditional Chinese, and Japanese. Website articles, news, newsletters, opinion, and release archives are not in this corpus. Returns bounded excerpts, commands when present, canonical links, official sources, and review dates. It never modifies state.
Paramètres, retour & exemple (9)
Paramètreslimit· integer · optionnelquery· string · requis
Natural-language task, concept, error, or exact CLI command.scope· string · optionnel · core
The only collection is core: balanced, source-checked CLI usage and feature manuals.offset· integer · optionnelworlds· array · optionnel
Optional canonical world filters: claude, gpt, or grok.products· array · optionnel
Optional product filters such as claude-code, codex, or grok-build.languages· array · optionnel
Optional locale filters: en, zh-tw, or ja.content_types· array · optionnel
Optional content filters, for example tutorial or field-guide.source_status· array · optionnel
Optional provenance filter. Every published manual is source-checked.
Exemple d'appel{"name": "worlds_search_knowledge", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "items": [], "query": "texte", "scope": "core", "total": 1, "offset": 1, "has_more": true, "next_offset": 1}}
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 ».