io.github.mjaskolski/wondel-skills-mcp

Est-ce que io.github.mjaskolski/wondel-skills-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.mjaskolski/wondel-skills-mcp » 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

• get_journey≈ 478 tokens

  One guided journey as a phase plan: the ordered skills, the decision question each phase answers, the docs/ file it writes, and which phases are go/no-go gates. Pass slug for a known journey, or goal to have one picked.

  Paramètres, retour & exemple (3)

  Paramètres

  • goal · string · optionnel
    What you are trying to achieve, if you do not know which journey fits
  • slug · string · optionnel
    Journey slug, e.g. "grow-website"
  • context · string · requis
    Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name.

  Exemple d'appel

  {"name": "get_journey", "arguments": {"context": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "next": "texte", "slug": "texte", "notFor": [], "phases": [], "install": "texte", "tagline": "texte", "useWhen": [], "artifacts": [], "canonical": "texte", "definition": "texte"}}

• get_skill≈ 750 tokens

  Metadata for one skill or journey: its definition, when to use it, when not to, and related slugs. Deliberately cheap (~300 tokens) so you can check a candidate before committing context to it. Pass sections to widen, or sections:["all"] for the whole page. This does not return the skill instructions — load_skill does.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Skill or journey slug, e.g. "refactoring-ui" or "create-business"
  • context · string · requis
    Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name.
  • sections · array · optionnel
    Which parts to return. Default: definition, use_when, not_for, related. "all" returns the full page.

  Exemple d'appel

  {"name": "get_skill", "arguments": {"slug": "texte", "context": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"book": {}, "faqs": [], "kind": "skill", "name": "texte", "next": "texte", "slug": "texte", "notFor": [], "phases": [], "source": "texte", "install": "texte", "related": [], "updated": "texte"}}

• load_skill≈ 237 tokens

  The skill's actual instructions — the upstream SKILL.md, ready to follow in this session with nothing installed. The response also lists the skill's reference files with their token cost, so you can pull deeper material on demand by calling again with part set to a filename.

  Paramètres, retour & exemple (3)

  Paramètres

  • part · string · optionnel
    "core" (default) for SKILL.md, or a reference filename from a previous response
  • slug · string · requis
    Skill or journey slug
  • context · string · requis
    Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name.

  Exemple d'appel

  {"name": "load_skill", "arguments": {"slug": "texte", "context": "texte"}}

  Exemple de retour

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

• recommend_skills≈ 614 tokens

  Route a task to the right skills. Describe the job in your own words and this returns which skills to load first, which to skip whenever a skill's own "not for" line rules it out for this task — quoted verbatim — and a guided journey when the task spans a whole project rather than one step. This is the tool to reach for first.

  Paramètres, retour & exemple (5)

  Paramètres

  • max · integer · optionnel
    How many skills to return (default 3)
  • task · string · requis
    The job to be done, in your own words — a full sentence beats a keyword
  • phase · string · optionnel · audit | build | launch
    Where in the work you are
  • stack · string · optionnel
    Language, framework or platform, if it narrows the answer
  • context · string · requis
    Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name.

  Exemple d'appel

  {"name": "recommend_skills", "arguments": {"task": "texte", "context": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"next": "texte", "task": "texte", "then": [], "avoid": [], "journey": {}, "loadFirst": []}}

• search_skills≈ 534 tokens

  Search 51 book-based agent skills and 14 guided journeys by keyword or phrase. Each skill is matched against its own trigger text, so plain task language works ("my UI looks amateur", "pricing", "dark mode"). Returns compact hits, each quoting the line that matched. Use recommend_skills instead when you have a task rather than a keyword.

  Paramètres, retour & exemple (5)

  Paramètres

  • kind · string · optionnel · skill | journey | all
    Restrict to single skills or guided journeys
  • limit · integer · optionnel
    Maximum hits (default 8)
  • query · string · requis
    Keyword, phrase, slug or plain description of the problem
  • context · string · requis
    Why are you calling this tool? One line on the user's actual task, in their words — not a restatement of the tool name.
  • category · string · optionnel · design | marketing | sales | product | strategy | team | code | architecture
    Restrict to one domain

  Exemple d'appel

  {"name": "search_skills", "arguments": {"query": "texte", "context": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"next": "texte", "query": "texte", "total": 1, "results": []}}

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://skills.wondel.ai/mcp