FillTrust security questionnaire corpus

Guidance for answering vendor security questionnaires. Every result carries the page it came from.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
92%
Vollständigkeit des Schemas
70%
Qualität der Benennung
100%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.

Kontextkosten

~515Tokens (Tool-Definitionen)
~440 BTypische Antwortgröße
Minimale Auswirkung auf die Aufmerksamkeit (0.40% von 128k Kontext)

Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.

Installieren

Installation mit einem Klick

Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:

{
  "mcpServers": {
    "questions": {
      "url": "https://www.filltrust.com/api/mcp"
    }
  }
}

Remote-Endpunkte

https://www.filltrust.com/api/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (5)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟢search_questions(query, limit)

Find guidance on how to answer a security questionnaire question. Search by the question text, a control area, or a standard and control identifier such as CEK-03. Returns matching entries with the URL of the page each came from.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The questionnaire question, or words from it. Pasting the row from the spreadsheet works."
    },
    "limit": {
      "type": "integer",
      "description": "How many results to return. Defaults to 8.",
      "minimum": 1,
      "maximum": 25
    }
  },
  "required": [
    "query"
  ]
}
🟢get_question(slug)

The complete published guidance for one questionnaire question: what it is really asking, which of your documents answers it, what evidence to attach, a model answer with the specifics left blank, the ways it usually goes wrong, and the standards that ask it with their verified control references.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search_questions result, for example \"encryption-at-rest\"."
    }
  },
  "required": [
    "slug"
  ]
}
🟢list_standards

Which questionnaire standards this corpus answers questions from, how many questions each has, and which controls are cited. Standards whose control lists are proprietary are named without reference numbers, on purpose.

Eingabe-Schema

{
  "type": "object",
  "properties": {}
}
🟢get_filltrust_posture

FillTrust's own answers to the questions it exists to answer, for anyone assessing it as a vendor. Includes the answers that are "no".

Eingabe-Schema

{
  "type": "object",
  "properties": {}
}
🟢get_questionnaire_statistics(questionnaire)

Measured counts from 146 real vendor security questionnaires (17,697 questions) published by universities, purchasing consortia and companies: which topics are asked most, and detailed profiles of the questionnaires that have a name people use, such as HECVAT and CAIQ. Use this when asked what a security questionnaire contains, how long one is, or what a named questionnaire asks about. These are counts from real files rather than an estimate.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "questionnaire": {
      "type": "string",
      "description": "Optional. A named questionnaire to profile, for example \"HECVAT\" or \"CAIQ\". Omit for the corpus-wide topic counts."
    }
  }
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet5 Tools
verifiziertVersion nicht aufgezeichnet5 Tools