dev.xpansion/xfms

Est-ce que dev.xpansion/xfms est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.xpansion/xfms » 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 7 outils

• benchmark≈ 616 tokens

  The live test: the 5 proven models and 1 promising newcomer from discovery do the person's real tasks side by side, every requirement is judged, and the results pick the winner. First call (session + tasks) returns the estimate and an offer — nothing is spent. Show the person the cost; only when they agree, call again with offer and go=true. Runs on the person's OpenRouter key (X-OpenRouter-Key header). Save the returned report as a local file.

  Paramètres, retour & exemple (9)

  Paramètres

  • go · boolean · optionnel
    The person approved the estimate. Spends on their key.
  • offer · string · optionnel
    The offer from the estimate. Pass it with go=true to run.
  • tasks · array · optionnel
    The person's real work to test on, real examples first. Write extra tasks yourself only for the gaps XFMS names, with source 'made up'. Images as data URLs.
  • ratings · object · optionnel
    Blind ratings: {task id: {letter: good|ok|poor}}, with test_session.
  • session · string · requis
    The sealed session from a finished discover conversation.
  • overruled · array · optionnel
    Failures the person accepts, as 'model id|requirement words'.
  • test_session · string · optionnel
    From a finished run, to overrule failures without rerunning.
  • current_model · string · optionnel
    OpenRouter id of the model the job uses now, if any.
  • runs_per_month · number · optionnel
    Roughly how many times a month the job runs, if known.

  Exemple d'appel

  {"name": "benchmark", "arguments": {"session": "texte"}}

  Exemple de retour

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

• compare≈ 571 tokens

  Same live test as benchmark, but on the models the person names (model_ids). Needs a finished discover session so every requirement is judged. Estimate first, then go=true.

  Paramètres, retour & exemple (10)

  Paramètres

  • go · boolean · optionnel
    The person approved the estimate. Spends on their key.
  • offer · string · optionnel
    The offer from the estimate. Pass it with go=true to run.
  • tasks · array · optionnel
    The person's real work to test on, real examples first. Write extra tasks yourself only for the gaps XFMS names, with source 'made up'. Images as data URLs.
  • ratings · object · optionnel
    Blind ratings: {task id: {letter: good|ok|poor}}, with test_session.
  • session · string · requis
    The sealed session from a finished discover conversation.
  • model_ids · array · optionnel
    The OpenRouter ids of the models the person named.
  • overruled · array · optionnel
    Failures the person accepts, as 'model id|requirement words'.
  • test_session · string · optionnel
    From a finished run, to overrule failures without rerunning.
  • current_model · string · optionnel
    OpenRouter id of the model the job uses now, if any.
  • runs_per_month · number · optionnel
    Roughly how many times a month the job runs, if known.

  Exemple d'appel

  {"name": "compare", "arguments": {"session": "texte"}}

  Exemple de retour

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

• discover≈ 736 tokens

  Discovery: finds the true requirements of the person's job before any model is chosen. Start with purpose: the reply carries the discovery instructions and the evidence catalogue. YOU ask the person the questions (one thing each, plain words, offering the returned choices); then call again with the sealed session, their answers and your structured updates. Each reply gives progress, rejected updates with reasons, next targets, answer choices from live data and a shortlist. At most 5 rounds. Ends with a confirmation view; call with confirm=true once the person agrees. The person can stop any time (end_now=true). Nothing about the person is stored by XFMS.

  Paramètres, retour & exemple (8)

  Paramètres

  • answers · object · optionnel
    The person's answers this round, keyed by the question you asked them (short key or the question text), in their exact words. For an XFMS question the person already answered earlier, send {"choice": choice id, "from_earlier": their exact earlier words} instead of asking it.
  • confirm · boolean · optionnel
    The person agrees with the confirmation view.
  • context · array · optionnel
    Optional, with the person's consent: short labelled excerpts (sample inputs, a conversation summary). Used for this request only, never kept.
  • end_now · boolean · optionnel
    The person wants to stop and see the best result so far.
  • purpose · string · optionnel
    The job the person wants an AI model for, in their own words. Needed to start.
  • session · string · optionnel
    The sealed session value from the previous discover response. Pass it back unchanged.
  • updates · object · optionnel
    What you learned from the answers, in the format the first discover reply's instructions give: conclusions, requirements, shapes, open_items, item_moves, relation, usage, survivors_matter, pushback. XFMS checks each against its rules and reports any it rejects.
  • corrections · array · optionnel
    Changes the person makes in the confirmation view: {requirement_id, field, value}.

  Exemple d'appel

  {"name": "discover", "arguments": {"answers": {}, "confirm": true, "context": [], "end_now": true, "purpose": "texte", "session": "texte"}}

  Exemple de retour

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

• field_results≈ 165 tokens

  Results from real comparisons on Model Source for one kind of job (call with no job_type for the list): which models passed, how often, which won, typical cost per task and the most common failure. Counted without anyone's job details. A starting point; test on the person's own work before choosing.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_type · string · optionnel
    One key from the list returned when called without it.

  Exemple d'appel

  {"name": "field_results", "arguments": {"job_type": "texte"}}

  Exemple de retour

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

• pick≈ 186 tokens

  The single best proven model for a job worked out with discover, with why and the runners-up. Pass the discover session.

  Paramètres, retour & exemple (1)

  Paramètres

  • session · string · requis
    The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first.

  Exemple d'appel

  {"name": "pick", "arguments": {"session": "texte"}}

  Exemple de retour

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

• rank≈ 234 tokens

  The full shortlist for a job worked out with discover: 5 proven models and 1 promising newcomer, each with its standing on every requirement, plus near misses and what would change the order. Pass the discover session.

  Paramètres, retour & exemple (1)

  Paramètres

  • session · string · requis
    The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first.

  Exemple d'appel

  {"name": "rank", "arguments": {"session": "texte"}}

  Exemple de retour

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

• watch_job≈ 458 tokens

  Saves a finished job for XF Model Watch, which re-tests it as new models arrive and emails the person only when a model passes every must-have and ranks higher on their priorities. Needs a signed-in subscriber. Ask the person first: Model Watch keeps the job and its example tasks (encrypted, deletable any time). Pass consent=true only if they agree. Pass the discover session, and either test_session from a finished comparison or the tasks, plus the model they use now. The first check runs as soon as the job is saved. To re-check a job the person already watches, pass check_now with the job's id or title instead (once a day per job; the result is emailed and shown at /account).

  Paramètres, retour & exemple (8)

  Paramètres

  • tasks · array · optionnel
    Example tasks, if no test_session.
  • title · string · optionnel
    A short name for the job, in the person's words.
  • consent · boolean · optionnel
    The person agreed to Model Watch keeping this job.
  • session · string · optionnel
    The discover session.
  • check_now · integer|string · optionnel
    Check a job they already watch now: its id or title. Leave out when saving a job.
  • test_session · string · optionnel
    From a finished comparison; carries its tasks.
  • current_model · string · optionnel
    OpenRouter id of the model the job uses now.
  • runs_per_month · number · optionnel
    Roughly how many times a month the job runs, if known.

  Exemple d'appel

  {"name": "watch_job", "arguments": {"tasks": [], "title": "texte", "consent": true, "session": "texte", "check_now": 1, "test_session": "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://xfms.xpansion.dev/mcp