SpinGras

EU AI Act Article 4 (AI literacy) readiness check and intro booking with SpinGras, Amsterdam.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
88%
Vollständigkeit des Schemas
73%
Qualität der Benennung
95%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Befunde (1)

  • LOWTool 'list_services' description lacks action verbin list_services

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

Kontextkosten

~1,057Tokens (Tool-Definitionen)
~1.9 KBTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (0.83% 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": {
    "mcp": {
      "url": "https://mcp.spingras.io/mcp"
    }
  }
}

Remote-Endpunkte

https://mcp.spingras.io/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (4)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟢list_services

Company facts and the four ways to work with SpinGras: workshop, 90-day rollout, keynote, retainer.

Eingabe-Schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢assess_article4_readiness(usesAi, staffUsingAi, hasAiUsePolicy, trainingDelivered, trainingRecorded, ...)

Checks an organisation's AI literacy measures against Article 4 of the EU AI Act and returns prioritised gaps with sources. Deterministic, not legal advice.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "usesAi": {
      "type": "boolean",
      "description": "Does anyone in the organisation use AI tools (e.g. ChatGPT, Copilot) or AI systems for work?"
    },
    "staffUsingAi": {
      "type": "integer",
      "minimum": 0,
      "maximum": 1000000,
      "description": "Approximate number of staff using AI for work"
    },
    "hasAiUsePolicy": {
      "type": "boolean",
      "description": "Is there written guidance on which AI tools may be used and for what?"
    },
    "trainingDelivered": {
      "type": "boolean",
      "description": "Have staff who use AI received any AI literacy training or guidance?"
    },
    "trainingRecorded": {
      "type": "boolean",
      "description": "Is that training documented (who, when, what)?"
    },
    "trainingRoleSpecific": {
      "type": "boolean",
      "description": "Is training matched to roles and the AI systems each role uses?"
    },
    "sensitiveUseCases": {
      "type": "boolean",
      "description": "Is AI used for decisions about people (hiring, credit, customers' eligibility) or with sensitive data?"
    }
  },
  "required": [
    "usesAi",
    "staffUsingAi",
    "hasAiUsePolicy",
    "trainingDelivered",
    "trainingRecorded",
    "trainingRoleSpecific",
    "sensitiveUseCases"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_intro_slots(from, days, timeZone)

Returns open 30-minute intro call slots with SpinGras, grouped by date.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "from": {
      "description": "First date to check, YYYY-MM-DD. Defaults to today.",
      "type": "string",
      "format": "date",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"
    },
    "days": {
      "default": 7,
      "type": "integer",
      "minimum": 1,
      "maximum": 14
    },
    "timeZone": {
      "default": "Europe/Amsterdam",
      "description": "IANA time zone for returned times",
      "type": "string",
      "maxLength": 64,
      "pattern": "^[A-Za-z_]+(\\/[A-Za-z0-9_+-]+){0,2}$|^UTC$"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢request_intro(name, email, company, topic, date)

Builds a prefilled booking link for a 30-minute intro call. Does not book anything: give the link to the user to confirm a time themselves.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100
    },
    "email": {
      "type": "string",
      "maxLength": 254,
      "format": "email",
      "pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
    },
    "company": {
      "type": "string",
      "maxLength": 100
    },
    "topic": {
      "description": "What the user wants to discuss",
      "type": "string",
      "maxLength": 500
    },
    "date": {
      "description": "Preferred date, YYYY-MM-DD",
      "type": "string",
      "format": "date",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet4 Tools