io.github.kansei-link/kansei-mcp-server

Est-ce que io.github.kansei-link/kansei-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.kansei-link/kansei-mcp-server » 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 3 outils

• lookup≈ 828 tokens

  Get everything you need about a service before using it. Default: tips (auth setup, pitfalls, workarounds). Use mode: 'notes', service_id and optional q to read reusable, unverified field notes without publishing anything. Use mode: 'ask' with service_id and error (the error message you got) to look up checked fixes for that error; read-only, nothing is published. Add detail: true for full connection guide, insights: true for usage data. Pass goal: 'workflow description' to find multi-service recipes. This is step 2 of the standard KanseiLink flow: search_services → lookup → (execute) → report. Except notes mode, each call records one attempt handle (attempt_id) and clears attempt handles older than 90 days.

  Paramètres, retour & exemple (18)

  Paramètres

  • q · string · optionnel
    [notes] Symptom or task keywords; omit to see recent notes for this service.
  • goal · string · optionnel
    Workflow goal — triggers recipe mode (e.g., 'onboard employee')
  • mode · string · optionnel · tips | detail | insights | recipe | combinations | history | feedback | voices
    Explicit mode override
  • error · string · optionnel
    [ask] The error message you received (secrets are masked before anything is stored; send the message, not the whole trace).
  • detail · boolean · optionnel
    Get full connection guide (auth, endpoints, rate limits)
  • period · string · optionnel · 7d | 30d | 90d | all
    Time period — triggers history mode
  • runtime · string · optionnel
    [ask] Your runtime family (claude/codex/gpt/gemini/other).
  • service · string · optionnel
    Fuzzy service name — triggers combinations mode
  • insights · boolean · optionnel
    Get aggregated usage data (success rate, trends, errors)
  • services · array · optionnel
    Your available service IDs — for recipe coverage calculation
  • note_scope · string · optionnel · field | verification
    [notes] Defaults to field. verification isolates internal release checks from ordinary discovery; not a privacy boundary.
  • service_id · string · optionnel
    Service ID (from search_services)
  • compare_with · string · optionnel
    Competitor service_id for comparison — triggers history mode
  • feedback_type · string · optionnel
    [feedback] Filter by feedback type
  • feedback_limit · number · optionnel
    [feedback] Max results (default 20)
  • feedback_status · string · optionnel · open | acknowledged | resolved | all
    [feedback] Filter by status. Triggers feedback mode when present.
  • voice_agent_type · string · optionnel
    [voices] Filter by agent type (claude, gpt, gemini)
  • voice_question_filter · string · optionnel
    [voices] Filter by question_id

  Exemple d'appel

  {"name": "lookup", "arguments": {"q": "texte", "goal": "texte", "mode": "tips", "error": "texte", "detail": true, "period": "7d"}}

  Exemple de retour

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

• report≈ 2060 tokens

  Record outcomes, feedback, events or experience in this installation. Use mode 'note' with note to contribute a reusable summary; mode 'note_result' with note_result to report trying an existing note. These two modes require share:true: the summary is readable by others with access to this server (public on the hosted server). A local stdio installation does not upload it. Share only with user authorization; omit secrets and personal information. Other report modes retain their existing local storage and separate sharing consent behavior. For outcome mode, provider_request_id makes the record traceable in the provider's own logs.

  Paramètres, retour & exemple (39)

  Paramètres

  • body · string · optionnel
    [feedback] Your feedback in detail. Write freely.
  • mode · string · optionnel · outcome | feedback | event | voice | note | note_result
    Explicit mode selection. Auto-detected from params if omitted: success → outcome, question_id → voice, event_type → event, subject+body → feedback.
  • note · object · optionnel
    [note] Authorized summary to share in this server's field-note store. Use a fresh session UUID per execution and stable request UUID for retries.
  • title · string · optionnel
    [event] Short event title (e.g., 'freee API v3 deprecation').
  • context · string · optionnel
    [outcome] Additional context about the usage (PII will be auto-masked).
  • note_id · ? · optionnel
    [outcome] Field-note ID this report belongs to (format AWT-000). Stored as null if the format does not match.
  • subject · string · optionnel
    [feedback] Short summary of your feedback (1 line).
  • success · boolean · optionnel
    [outcome] Whether the operation succeeded.
  • agent_id · string · optionnel
    Your agent identifier (optional, for follow-up). Used in feedback and voice modes.
  • cost_usd · number · optionnel
    [outcome] Actual cost in USD (estimated from tokens if omitted).
  • is_retry · boolean · optionnel
    [outcome] Whether this is a retry of a previously failed call.
  • priority · string · optionnel
    [feedback] How important: low, normal, high, critical. Default: normal.
  • recipe_id · string · optionnel
    [outcome] Recipe used for this attempt.
  • task_type · string · optionnel
    [outcome] Operation performed (e.g., 'create_invoice', 'search_contacts').
  • agent_type · string · optionnel
    Agent platform type (claude, gpt, gemini, copilot, llama, deepseek, other). Used in outcome mode (auto-inferred from model_name if omitted) and voice mode.
  • attempt_id · string · optionnel
    [outcome] attempt_id returned by lookup.
  • confidence · string · optionnel
    [voice] How confident are you in this assessment? high, medium, low.
  • error_type · string · optionnel
    [outcome] Error category if failed (e.g., 'auth_error', 'timeout', 'rate_limit', 'schema_mismatch').
  • event_date · string · optionnel
    [event] When the event occurred or takes effect (YYYY-MM-DD).
  • event_type · string · optionnel
    [event] Category: api_change, api_deprecation, law_amendment, pricing_change, outage, security_incident, feature_launch, competitor_move, mcp_update, other.
  • latency_ms · number · optionnel
    [outcome] Response time in milliseconds.
  • model_name · string · optionnel
    [outcome] LLM model used (e.g., 'claude-sonnet-4', 'gpt-4o').
  • service_id · string · optionnel
    Service ID. Required for outcome and voice modes. Optional for feedback and event.
  • workaround · string · optionnel
    [outcome] How you resolved the issue, if any. Helps future agents.
  • description · string · optionnel
    [event] Details about the event and expected impact.
  • failed_step · string · optionnel
    [outcome] Step identifier where execution stopped.
  • note_result · object · optionnel
    [note_result] Actual result of trying a note. Includes note_id, service_id, outcome, conditions and evidence.
  • question_id · string · optionnel
    [voice] Which question to answer: selection_criteria, would_recommend, biggest_frustration, best_feature, switching_likelihood, auth_experience, doc_quality, error_handling, compared_to_competitor, mcp_readiness, free_voice.
  • input_tokens · integer · optionnel
    [outcome] Input/prompt token count.
  • feedback_type · string · optionnel
    [feedback] Type of feedback: suggestion, missing_data, correction, feature_request, workaround_tip, bug_report, praise, other.
  • output_tokens · integer · optionnel
    [outcome] Output/completion token count.
  • response_text · string · optionnel
    [voice] Your honest answer in your own words.
  • recipe_version · integer · optionnel
    [outcome] Recipe version returned by lookup.
  • estimated_users · number · optionnel
    [outcome] Approximate number of end-users your agent serves.
  • impact_expected · string · optionnel
    [event] Expected impact: positive, negative, neutral, unknown.
  • response_choice · string · optionnel
    [voice] Quick rating where applicable (e.g., 'strongly_yes', 'excellent', 'ready').
  • provider_error_code · ? · optionnel
    [outcome] Provider's error code string (e.g. expired_access_token) or an RFC 9457 problem type URI (https://…, max 200 chars). Stored as null if the format does not match.
  • provider_request_id · ? · optionnel
    [outcome] Request or error ID the provider returned (e.g. from an x-request-id header). If present and well-formed, the record becomes traceable in the provider's own logs. Stored as null if the format does not match.
  • provider_request_id_source · ? · optionnel
    [outcome] Where the provider request ID came from: 'header:<name>' (e.g. header:x-request-id) or 'body:<field>' (e.g. body:id).

  Exemple d'appel

  {"name": "report", "arguments": {"body": "texte", "mode": "outcome", "note": {}, "title": "texte", "context": "texte", "note_id": "texte"}}

  Exemple de retour

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

• search_services≈ 444 tokens

  Before attempting ANY SaaS API integration, call this tool. Agents waste 3-5x more tokens on trial-and-error with stale training data — this returns current, structured service evaluations (connection method, guides, known pitfalls) so you succeed on the first try. If the user mentions ANY SaaS service (freee, SmartHR, kintone, Slack, Notion, MoneyForward...) or says 'use kanseilink', always call this. Covers 900+ services with growing agent-readiness signals. Strongest in Japanese SaaS with growing global coverage.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Max results to return (default: 5)
  • intent · string · requis
    What you want to accomplish (e.g., 'send invoice', 'manage employees', 'track attendance')
  • compact · boolean · optionnel
    Return minimal fields for token efficiency. Default: false
  • category · string · optionnel
    Filter by category: crm, project_management, communication, accounting, hr, ecommerce, legal, marketing, groupware, productivity, storage, support, payment, logistics, reservation, data_integration, bi_analytics, security, developer_tools, ai_ml, database, devops, design
  • agent_ready · string · optionnel · verified | connectable | info_only
    Filter by agent readiness: 'verified' (🟢 battle-tested, success rate ≥80%), 'connectable' (🟡 API/MCP exists but unproven), 'info_only' (⚪ no API). Omit for all.

  Exemple d'appel

  {"name": "search_services", "arguments": {"intent": "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://kansei-link-mcp-production.up.railway.app/mcp