io.github.atomeam/void

Est-ce que io.github.atomeam/void est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.atomeam/void » 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 18 outils

• ask_void≈ 230 tokens

  Ask Verse a question in plain words and get its answer: a short, direct answer from Verse's answer engine (a-to-mind.com), citing the Wikipedia pages it drew on when they match. Ask about Verse itself ("what are you building?") and it answers from its own live facts. Up to 12 model answers a minute per caller; a repeated question may come from the 7-day cache.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The question, in plain words (3 to 600 characters).
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "ask_void", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• drive_time≈ 191 tokens

  How long the drive is between two places, and how far, from a live routing service (the public OSRM router, no key; road network at free-flow speed, so no live traffic). Places by name (looked up with Open-Meteo's geocoder) or as "lat,lon". Verse's rides family checks this same router once a day.

  Paramètres, retour & exemple (2)

  Paramètres

  • to · string · requis
    Where to: a place name or "lat,lon".
  • from · string · requis
    Where from: a place name ("San Francisco") or "lat,lon".

  Exemple d'appel

  {"name": "drive_time", "arguments": {"to": "texte", "from": "texte"}}

  Exemple de retour

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

• meteor_showers≈ 127 tokens

  The meteor showers active on a date (strongest first, with days to each peak and the peak rate) and the next peak on or after it, from the IMO calendar of the major showers.

  Paramètres, retour & exemple (1)

  Paramètres

  • date · string · optionnel
    An ISO date or date-time (UTC). Leave it out for now.

  Exemple d'appel

  {"name": "meteor_showers", "arguments": {"date": "texte"}}

  Exemple de retour

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

• moon_phase≈ 123 tokens

  The moon's illuminated fraction, whether it is waxing or waning, and the phase's name for a moment, from Meeus' formulas (Astronomical Algorithms, ch. 47-48).

  Paramètres, retour & exemple (1)

  Paramètres

  • date · string · optionnel
    An ISO date or date-time (UTC). Leave it out for now.

  Exemple d'appel

  {"name": "moon_phase", "arguments": {"date": "texte"}}

  Exemple de retour

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

• review_code≈ 229 tokens

  Verse's instant code review: pattern checks for bugs, risks and style in pasted code or a diff's added lines, in many languages. The same checks a-to-mind.com runs when someone asks Verse to review code. No model; the closer read is not included. Its structured result says basis 'patterns' and confidence 'low'.

  Paramètres, retour & exemple (3)

  Paramètres

  • code · string · optionnel
    The code to review (up to 60,000 characters).
  • diff · string · optionnel
    A unified diff instead of code: only the added lines are reviewed, with their line numbers in the new file.
  • lang · string · optionnel
    The language, if known (javascript, python, go, rust, sql, ...).

  Exemple d'appel

  {"name": "review_code", "arguments": {"code": "texte", "diff": "texte", "lang": "texte"}}

  Exemple de retour

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

• review_code_closer≈ 281 tokens

  Verse's code review with the closer read: the instant checks, then an AI reviewer that confirms real findings, drops wrong ones and adds what the patterns missed, each quoting its line. The closer read needs a key in the MCP request's Authorization header (Bearer: a Verse Pro review key vr1.… or a Verse Code Review Pro license key; https://a-to-mind.com/code-review/#pro). Without one you get the instant checks and how to get it. The structured result says what it rests on: basis 'closer_read' (confidence 'reviewed') only when the closer read came back, else 'patterns' (confidence 'low').

  Paramètres, retour & exemple (3)

  Paramètres

  • code · string · optionnel
    The code to review (up to 60,000 characters).
  • diff · string · optionnel
    A unified diff instead of code: the added lines are reviewed.
  • lang · string · optionnel
    The language, if known.

  Exemple d'appel

  {"name": "review_code_closer", "arguments": {"code": "texte", "diff": "texte", "lang": "texte"}}

  Exemple de retour

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

• skill_constellation≈ 296 tokens

  Ask Verse's "constellation" skill (Sky and earth), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "what's that constellation", "constellations tonight", "where is Orion". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "what's that constellation".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_constellation", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_country≈ 289 tokens

  Ask Verse's "country" skill (Sky and earth), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "capital of australia", "population of japan", "capital of canada". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "capital of australia".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_country", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_define≈ 288 tokens

  Ask Verse's "define" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "define serendipity", "define ephemeral", "define ubiquitous". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "define serendipity".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_define", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_discovery≈ 306 tokens

  Skill Discovery (asked by Verse): what skills Verse has and how they are spread across its families, for an agent that wants to know where to look before it asks. Gives each family's id, name, what it is for, how many skills it holds, its share of all of Verse's skills (the distribution), and the skills in it by name with their rating; ask for one family, or only the skills at a rating. Read from a-to-mind.com/skills/families.json, rated from evidence only. Ask a skill by name through ask_void or the skill's own tool.

  Paramètres, retour & exemple (3)

  Paramètres

  • tier · string · optionnel · experiment | tested | checked | proven
    Only skills rated at least this high.
  • family · string · optionnel
    Only this family (an id from the result, e.g. numbers).
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_discovery", "arguments": {"tier": "experiment", "family": "texte", "response_type": "text"}}

  Exemple de retour

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

• skill_eclipse≈ 285 tokens

  Ask Verse's "eclipse" skill (Sky and earth), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "next eclipse", "next lunar eclipse", "upcoming eclipses". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "next eclipse".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_eclipse", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_film_metadata≈ 304 tokens

  Ask Verse's "film-metadata" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "find me a sci-fi film from the 80s", "films by Kurosawa", "movies directed by Hitchcock". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "find me a sci-fi film from the 80s".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_film_metadata", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_health≈ 273 tokens

  How far each of Verse's skills is checked, family by family (a-to-mind.com/skills/families.json). Every skill is rated from evidence only, never from how it describes itself: experiment (nothing checks it), tested, checked or proven (its own tests, the browser suite, real asks in Verse's benchmark). Gives the totals, each family's counts and share proven, the skills failing a benchmark ask, and which skills have their own tool here. Name a family to get each of its skills with its rating and why.

  Paramètres, retour & exemple (2)

  Paramètres

  • family · string · optionnel
    A family's id (families[].id in this tool's result, e.g. numbers) for its skills one by one.
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_health", "arguments": {"family": "texte", "response_type": "text"}}

  Exemple de retour

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

• skill_recipe≈ 290 tokens

  Ask Verse's "recipe" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "recipe for pancakes", "how do i make guacamole", "chicken recipes". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "recipe for pancakes".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_recipe", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_swaps≈ 298 tokens

  Ask Verse's "swaps" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "what can i swap for buttermilk", "substitute for eggs in baking", "baking powder substitute". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "what can i swap for buttermilk".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_swaps", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_technical_context≈ 304 tokens

  Ask Verse's "technical-context" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "why is rust unwrap a risk", "is unwrap risky in rust", "technical context for unwrap". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "why is rust unwrap a risk".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_technical_context", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_translate≈ 302 tokens

  Ask Verse's "translate" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "translate hello to spanish", "translate thank you to japanese", "translate good morning to french". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "translate hello to spanish".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_translate", "arguments": {"ask": "texte"}}

  Exemple de retour

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

• skill_words≈ 291 tokens

  Ask Verse's "words" skill (Words and the world), one of the proven skills with the most evidence that Verse offers over MCP (read-only): rated proven on a-to-mind.com from evidence (real asks in Verse's benchmark, its tests), never from how it describes itself. Asks like "synonym for happy", "how do you spell necessary", "what rhymes with orange". Over MCP it is answered the way ask_void is: Verse's answer engine (a model, citing Wikipedia when it matches; up to 12 a minute per caller). The skill itself works it out on its own card at the "open" link in the result.

  Paramètres, retour & exemple (2)

  Paramètres

  • ask · string · requis
    The ask in plain words (3 to 600 characters), e.g. "synonym for happy".
  • response_type · string · optionnel · text | raw_data | image
    What to get back: 'text' (default) or 'raw_data' (the structured result as JSON). 'image' is not offered yet.

  Exemple d'appel

  {"name": "skill_words", "arguments": {"ask": "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://a-to-mind.com/api/mcp