accueil / serveurs / IA & Mémoire / co.superforms/superforms
co.superforms/superforms
serveur MCP (Model Context Protocol) · superforms 0.2.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que co.superforms/superforms est sûr ?
Au dernier audit MCP Hub, le serveur MCP « co.superforms/superforms » 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 11 outils
- create_ask≈ 548 tokens
Create a voice-first Superforms answer link for human input. Backward-compatible alias for create_form.
Paramètres, retour & exemple (13)
Paramètresgoal· string · optionneltitle· string · optionnelprompt· string · optionnel
Plain-English ask or request. Use only when explicit questions are not already known.context· string · optionnel
Private context for smart follow-ups. Summarize relevant non-sensitive host-conversation context and append any extra context the creator provides. Never shown to respondents.questions· array · optionnel
Explicit questions to ask the respondent. Use this whenever questions already exist; preserve them exactly.persistent· boolean · optionnelfollowUpMode· string · optionnel · none | smart | deep_dive
For exactly one question, set this only after asking the creator "Want smart follow-up questions?" Use deep_dive for yes or none for no. For multiple questions, use none unless explicitly requested.responseMode· string · optionnel · voice_preferred | text_only | voice_onlyresponseLimit· string · optionnel · one | multiple
Use "one" for a form intended for one named person/client. Use "multiple" for forms, surveys, feedback, customers, users, and public/embedded links.questionContext· object · optionnelcreationSessionUrl· string · optionnelmax_total_questions· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.max_followups_per_question· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.
Exemple d'appel{"name": "create_ask", "arguments": {"goal": "texte", "title": "texte", "prompt": "texte", "context": "texte", "questions": [], "persistent": true}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - create_feedback_form≈ 564 tokens
Publish a voice-first feedback, cancellation, feature request, survey, or research form immediately after creator confirmation, with optional smart follow-ups.
Paramètres, retour & exemple (13)
Paramètresgoal· string · optionneltitle· string · optionnelprompt· string · optionnel
Plain-English ask or request. Use only when explicit questions are not already known.context· string · optionnel
Private context for smart follow-ups. Summarize relevant non-sensitive host-conversation context and append any extra context the creator provides. Never shown to respondents.questions· array · optionnel
Explicit questions to ask the respondent. Use this whenever questions already exist; preserve them exactly.persistent· boolean · optionnelfollowUpMode· string · optionnel · none | smart | deep_dive
For exactly one question, set this only after asking the creator "Want smart follow-up questions?" Use deep_dive for yes or none for no. For multiple questions, use none unless explicitly requested.responseMode· string · optionnel · voice_preferred | text_only | voice_onlyresponseLimit· string · optionnel · one | multiple
Use "one" for a form intended for one named person/client. Use "multiple" for forms, surveys, feedback, customers, users, and public/embedded links.questionContext· object · optionnelcreationSessionUrl· string · optionnelmax_total_questions· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.max_followups_per_question· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.
Exemple d'appel{"name": "create_feedback_form", "arguments": {"goal": "texte", "title": "texte", "prompt": "texte", "context": "texte", "questions": [], "persistent": true}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - create_form≈ 556 tokens
Publish a voice-first form link immediately after creator confirmation, collect human answers, and pipe responses back to the agent.
Paramètres, retour & exemple (13)
Paramètresgoal· string · optionneltitle· string · optionnelprompt· string · optionnel
Plain-English ask or request. Use only when explicit questions are not already known.context· string · optionnel
Private context for smart follow-ups. Summarize relevant non-sensitive host-conversation context and append any extra context the creator provides. Never shown to respondents.questions· array · optionnel
Explicit questions to ask the respondent. Use this whenever questions already exist; preserve them exactly.persistent· boolean · optionnelfollowUpMode· string · optionnel · none | smart | deep_dive
For exactly one question, set this only after asking the creator "Want smart follow-up questions?" Use deep_dive for yes or none for no. For multiple questions, use none unless explicitly requested.responseMode· string · optionnel · voice_preferred | text_only | voice_onlyresponseLimit· string · optionnel · one | multiple
Use "one" for a form intended for one named person/client. Use "multiple" for forms, surveys, feedback, customers, users, and public/embedded links.questionContext· object · optionnelcreationSessionUrl· string · optionnelmax_total_questions· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.max_followups_per_question· number · optionnel
Optional compatibility setting. Omit for adaptive one-question smart follow-ups.
Exemple d'appel{"name": "create_form", "arguments": {"goal": "texte", "title": "texte", "prompt": "texte", "context": "texte", "questions": [], "persistent": true}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_my_form_responses≈ 132 tokens
Read persisted raw responses for a form owned by the connected Superforms account. No per-form agent token is required.
Paramètres, retour & exemple (2)
ParamètresaskId· string · requissince· string · optionnel
Optional ISO timestamp cursor.
Exemple d'appel{"name": "get_my_form_responses", "arguments": {"askId": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_responses≈ 130 tokens
Fetch persisted raw responses for a Superforms ask. This is the MCP equivalent of the HTTP bridge answers endpoint.
Paramètres, retour & exemple (3)
ParamètresaskId· string · requissince· string · optionnelagentToken· string · requis
Exemple d'appel{"name": "get_responses", "arguments": {"askId": "texte", "agentToken": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - join_creation_session≈ 116 tokens
Join a Superforms homepage creation handoff session before creating the real form. Pass agentName with the client name, such as Codex, Claude Code, Claude, ChatGPT, or Cursor.
Paramètres, retour & exemple (2)
ParamètresagentName· string · optionnelcreationSessionUrl· string · requis
Exemple d'appel{"name": "join_creation_session", "arguments": {"creationSessionUrl": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_asks≈ 95 tokens
List recent asks for a provided private agent token.
Paramètres, retour & exemple (1)
ParamètresagentToken· string · requis
Exemple d'appel{"name": "list_asks", "arguments": {"agentToken": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_my_forms≈ 96 tokens
List forms owned by the connected Superforms account, including response counts and latest response timestamps.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "list_my_forms", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - update_creation_session≈ 395 tokens
Update a homepage creation handoff draft with the current form title, questions, and settings before the user clicks Set live.
Paramètres, retour & exemple (10)
Paramètresgoal· string · optionneltitle· string · optionnelcontext· string · optionnel
Private smart-follow-up context. Summarize relevant non-sensitive host-conversation context and append any extra context the creator provides. Never shown to respondents.questions· array · optionnel
Current draft questions to show in the live form preview.followUpMode· string · optionnel · none | smart | deep_diveresponseMode· string · optionnel · voice_preferred | text_only | voice_onlyresponseLimit· string · optionnel · one | multiple
Use one for a named person/client. Use multiple for feedback forms, surveys, customers, users, and public links.creationSessionUrl· string · requismax_total_questions· number · optionnel
Use 20 for deep-dive interviews.max_followups_per_question· number · optionnel
Use 0 by default. Use 1 only when smart follow-ups are explicitly requested.
Exemple d'appel{"name": "update_creation_session", "arguments": {"creationSessionUrl": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - watch_ask≈ 244 tokens
Wait up to two minutes and return as soon as an individual answer is saved, including answers received while an agent was reconnecting and while the form remains in progress. The wait ends when this call returns; nothing keeps watching afterward. Pass the returned nextSince as since to continue without repeating answers; the HTTP bridge also exposes an SSE stream endpoint.
Paramètres, retour & exemple (5)
Paramètresurl· string · requisaskId· string · optionnelsince· string · optionnel
ISO timestamp cursor from the last response the agent processed.timeoutMs· number · optionnel
Maximum wait in milliseconds, capped at 120000.agentToken· string · requis
Exemple d'appel{"name": "watch_ask", "arguments": {"url": "texte", "agentToken": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - watch_my_form_responses≈ 167 tokens
Return any existing individual answers immediately, or wait briefly until the respondent saves their next answer, even while the form remains in progress.
Paramètres, retour & exemple (3)
ParamètresaskId· string · requissince· string · optionnel
Optional ISO timestamp cursor.timeoutMs· number · optionnel
Maximum wait in milliseconds, capped at 120000.
Exemple d'appel{"name": "watch_my_form_responses", "arguments": {"askId": "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 ».