Skip to main content
Glama
CSOAI-ORG

NIS2 Compliance MCP

classify_entity

Classify an entity's NIS2 compliance scope (essential, important, or out-of-scope) and sector using employee count and turnover.

Instructions

Classify an entity's NIS2 scope (essential / important / out-of-scope) + sector. Size-cap rules (Article 2): essential if in Annex I AND medium-size (>50 FTE or >€10M) — generally large (>250 FTE or >€50M). Important if Annex II + medium-size.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: entity_description (str): The entity description to analyze or process. employees (int): The employees to analyze or process. turnover_million_eur (float): The turnover million eur to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
entity_descriptionYes
employeesNo
turnover_million_eurNo
api_keyNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • server.py:130-130 (registration)
    Tool registration via @mcp.tool() decorator on classify_entity function.
    @mcp.tool()
  • Main handler for classify_entity tool: checks access, rate limits, matches entity description against Annex I/II sectors, applies size threshold logic (Article 2), and returns JSON with classification (ESSENTIAL/IMPORTANT/OUT_OF_SCOPE), penalties, and next steps.
    def classify_entity(entity_description: str, employees: int = 0, turnover_million_eur: float = 0.0, api_key: str = "") -> str:
        """Classify an entity's NIS2 scope (essential / important / out-of-scope) + sector.
        Size-cap rules (Article 2): essential if in Annex I AND medium-size (>50 FTE or >€10M) — generally large (>250 FTE or >€50M). Important if Annex II + medium-size.
    
        Behavior:
            This tool is read-only and stateless — it produces analysis output
            without modifying any external systems, databases, or files.
            Safe to call repeatedly with identical inputs (idempotent).
            Free tier: 10/day rate limit. Pro tier: unlimited.
            No authentication required for basic usage.
    
        When to use:
            Use this tool when you need to assess, audit, or verify compliance
            requirements. Ideal for gap analysis, readiness checks, and generating
            compliance documentation.
    
        When NOT to use:
            Do not use as a substitute for qualified legal counsel. This tool
            provides technical compliance guidance, not legal advice.
    
        Args:
            entity_description (str): The entity description to analyze or process.
            employees (int): The employees to analyze or process.
            turnover_million_eur (float): The turnover million eur to analyze or process.
            api_key (str): The api key to analyze or process.
    
        Behavioral Transparency:
            - Side Effects: This tool is read-only and produces no side effects. It does not modify
              any external state, databases, or files. All output is computed in-memory and returned
              directly to the caller.
            - Authentication: No authentication required for basic usage. Pro/Enterprise tiers
              require a valid MEOK API key passed via the MEOK_API_KEY environment variable.
            - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are
              included in responses (X-RateLimit-Remaining, X-RateLimit-Reset).
            - Error Handling: Returns structured error objects with 'error' key on failure.
              Never raises unhandled exceptions. Invalid inputs return descriptive validation errors.
            - Idempotency: Fully idempotent — calling with the same inputs always produces the
              same output. Safe to retry on timeout or transient failure.
            - Data Privacy: No input data is stored, logged, or transmitted to external services.
              All processing happens locally within the MCP server process.
        """
        allowed, msg, tier = check_access(api_key)
        if not allowed:
            return json.dumps({"error": msg, "upgrade_url": UPGRADE_STRIPE_49})
        if err := _check_rate_limit(tier=tier):
            return json.dumps({"error": err, "upgrade_url": UPGRADE_STRIPE_49})
    
        d = entity_description.lower()
        matched_annex_i = [k for k, v in ANNEX_I_ESSENTIAL_SECTORS.items() if any(t in d for t in k.split("_")) or any(t in d for t in v.lower().split(","))]
        matched_annex_ii = [k for k, v in ANNEX_II_IMPORTANT_SECTORS.items() if any(t in d for t in k.split("_")) or any(t in d for t in v.lower().split(","))]
    
        # Size thresholds (Article 2.1 / Article 2.2 + Commission Recommendation 2003/361/EC)
        # Medium = 50+ FTE OR €10M+ turnover. Large = 250+ FTE OR €50M+.
        is_large = employees >= 250 or turnover_million_eur >= 50
        is_medium = employees >= 50 or turnover_million_eur >= 10 or is_large
        is_micro_small = not is_medium and (employees > 0 or turnover_million_eur > 0)
    
        # Classification
        status = "OUT_OF_SCOPE"
        classification = None
        if matched_annex_i and is_medium:
            status = "IN_SCOPE"
            classification = "ESSENTIAL"
        elif matched_annex_ii and is_medium:
            status = "IN_SCOPE"
            classification = "IMPORTANT"
        elif (matched_annex_i or matched_annex_ii) and is_micro_small:
            status = "OUT_OF_SCOPE_BY_SIZE"
            classification = "Below size thresholds (Annex I needs medium+; Annex II needs medium+)"
        elif matched_annex_i or matched_annex_ii:
            status = "LIKELY_IN_SCOPE (provide employees/turnover to confirm)"
    
        days_since = (datetime.now(timezone.utc) - ENFORCEMENT_DATE).days
        penalty_headline = (
            "Up to €10M or 2% of global annual turnover" if classification == "ESSENTIAL"
            else "Up to €7M or 1.4% of global annual turnover" if classification == "IMPORTANT"
            else "Not applicable (out of scope)"
        )
    
        return json.dumps({
            "status": status,
            "classification": classification,
            "matched_annex_i_sectors": matched_annex_i,
            "matched_annex_ii_sectors": matched_annex_ii,
            "size": "large" if is_large else "medium" if is_medium else "small/micro" if is_micro_small else "unknown",
            "penalties_headline": penalty_headline,
            "days_since_eu_enforcement": days_since,
            "eu_enforcement_date": ENFORCEMENT_DATE.isoformat(),
            "national_transposition_note": "Each Member State transposes NIS2 into national law; exact deadlines and competent authorities vary. Check your national CSIRT and the ENISA NIS360 tracker.",
            "registration_required": status.startswith("IN_SCOPE") or status == "LIKELY_IN_SCOPE (provide employees/turnover to confirm)",
            "next_step": "Run audit_article_21 to score your 10 risk-management measures.",
        }, indent=2)
  • Annex I and Annex II sector definitions used by classify_entity to match entity descriptions.
    ANNEX_I_ESSENTIAL_SECTORS = {
        "energy": "Energy — electricity, district heating/cooling, oil, gas, hydrogen",
        "transport": "Transport — air, rail, water, road",
        "banking": "Banking — credit institutions (overlaps DORA)",
        "financial_market_infra": "Financial market infrastructure — trading venues, CCPs",
        "health": "Health — healthcare providers, EU reference labs, R&D of medicinal products, manufacturing of medical devices critical during public health emergency",
        "drinking_water": "Drinking water — suppliers and distributors",
        "waste_water": "Waste water — collection, disposal, treatment",
        "digital_infrastructure": "Digital infrastructure — IXPs, DNS service providers, TLD name registries, cloud computing services, data centre services, content delivery networks, trust service providers, public electronic comms networks, public electronic comms services",
        "ict_service_management": "ICT service management (B2B) — MSPs, MSSPs",
        "public_administration": "Public administration — central government, regional authorities (as designated by Member States)",
        "space": "Space — operators of ground-based infrastructure supporting space services",
    }
    
    ANNEX_II_IMPORTANT_SECTORS = {
        "postal": "Postal and courier services",
        "waste_management": "Waste management",
        "chemicals": "Manufacture, production and distribution of chemicals",
        "food": "Production, processing and distribution of food",
        "manufacturing": "Manufacturing — medical devices & IVDs, computers/electronics/optical, electrical equipment, machinery, motor vehicles, other transport",
        "digital_providers": "Digital providers — online marketplaces, online search engines, social networking platforms",
        "research": "Research organisations",
    }
  • check_access helper called by classify_entity to validate API key.
    def check_access(api_key: str = ""):
        return _shared_check_access(api_key)
  • _check_rate_limit helper called by classify_entity to enforce free tier daily limit.
    def _check_rate_limit(caller: str = "anonymous", tier: str = "free") -> Optional[str]:
        if tier in ("pro", "professional", "enterprise"):
            return None
        now = datetime.now(timezone.utc)
        cutoff = now - timedelta(days=1)
        _usage[caller] = [t for t in _usage[caller] if t > cutoff]
        if len(_usage[caller]) >= FREE_DAILY_LIMIT:
            return (
                f"Free tier limit reached ({FREE_DAILY_LIMIT}/day). Unlock unlimited + "
                f"audit_all_obligations + signed certificates for £49/mo: {UPGRADE_STRIPE_49}"
            )
        _usage[caller].append(now)
        return None
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description covers side effects (read-only, stateless), authentication (no auth for basic, API key for pro), rate limits (free 10/day), error handling, idempotency, and data privacy. Very thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections, but contains redundancy (e.g., 'Behavioral Transparency' repeated). Some sentences could be merged for better conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers size-cap rules, rate limits, auth, and error handling. With an output schema present, return values are not needed. Lacks clarity on possible sector values, but overall adequate for agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage. The 'Args' section adds generic phrases like 'to analyze or process' that barely clarify meaning. Although the main description mentions size-cap rules, parameter-specific semantics are weak.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool classifies an entity's NIS2 scope (essential/important/out-of-scope) and sector, with specific rules. It distinguishes from siblings like classify_incident by focusing on entity classification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'When to use' and 'When NOT to use' sections provide context for gap analysis and compliance checks, and warn against legal advice. However, it does not contrast with sibling tools or specify when to prefer alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CSOAI-ORG/nis2-compliance-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server