ClevSec EU compliance tools

Use when someone asks how risky an AI agent or assistant setup is ('is it safe to let our agent read email and send replies?', 'what are the risks of this agent?'). Call without answers to get 9 questions on what the agent can do and 11 on the controls that limit it. Call with answers to get a 0-100 residual risk score (0 = lowest), a risk level, red flags such as an exfiltration path, and the missing controls with actions and OWASP, GDPR and AI Act references. A self-assessment from the user's answers, not a scan or test of the agent.

Use when someone asks whether the EU AI Act applies to an AI system or model, how it is classified or what they must do ('is our recruitment tool high-risk?', 'does the AI Act apply to our chatbot?', 'what are our AI Act obligations as a deployer?'). Call without answers to get the questions. Call with answers about one system to get whether it is in scope, the role (provider, deployer, importer, distributor; Art. 25 role change), the classification (prohibited, high-risk under Annex I or III, Art. 6(3) exception, Art. 50 transparency, minimal risk, GPAI model), and each obligation with its article and the date it applies from, using the dates of the AI Act as amended by the 2026 Digital Omnibus (Regulation (EU) 2026/1744). A self-assessment from the user's answers, not legal advice.

Use when someone asks whether their cookie banner or cookie consent is compliant in the EU (ePrivacy Art. 5(3) and GDPR consent rules). Call without answers to get the checklist items by area, critical ones marked. Call with yes, partial or no per item to get a score, a compliance label and the open items.

Use after cookie_consent_check when the user wants to fix their cookie consent. Returns every open item with the fix, its legal source (ePrivacy, GDPR, CJEU Planet49, EDPB) and a 30/60/90-day roadmap. Requires ClevSec Pro.

Use when a manufacturer of hardware or software sold in the EU learns of an actively exploited vulnerability or a security incident in its product. Applies Art. 14 of the Cyber Resilience Act (Regulation (EU) 2024/2847), in force since 11 September 2026: whether a report is due, the 24-hour, 72-hour and final report deadlines, where to report, and informing users.

Use after cyber_risk_score when the user wants to reduce their risk. Returns every gap with a recommended action, a priority, NIST CSF 2.0 and NIS2 references and a 30/60/90-day roadmap (MFA, encryption, patching, incident response and backups first). Requires ClevSec Pro.

Use for a quick view of a small organisation's cyber risk ('how secure are we?', 'what is our cyber risk score?'). Call without answers to get 15 weighted questions on access, data, systems, people, incident response and backups. Call with yes, partial or no per question to get a 0-100 score, a risk level and a score per category.

Use when someone maps personal data flows or builds GDPR records of processing activities (ROPA, Art. 30). Give the flows (name, purpose, data categories, recipients, legal basis, retention, transfers); returns, per flow, what an Art. 30 record still lacks, plus the allowed values for categories, legal bases and safeguards.

Use after data_flow_record_check for a compliance review of each personal data flow: legal basis, special category and children's data, consent and legitimate interest records, retention, international transfer tools and transfer impact assessments, and DPIA need, with an action, GDPR article and 30/60/90-day roadmap. Requires ClevSec Pro.

Use for 'what does DORA require?', DORA compliance checklists or gap reviews. Returns the core DORA (Regulation (EU) 2022/2554) requirements for financial entities, grouped by section with the article for each, leaving out those that DORA itself disapplies for microenterprises or for entities under the simplified ICT risk management framework of Art. 16.

Use when a bank, insurer, investment firm, payment or crypto-asset firm or other financial entity has an IT outage, cyber attack or data incident and asks whether it must be reported under DORA. Classifies the ICT-related incident as major or not under DORA, applying the criteria and materiality thresholds of Commission Delegated Regulation (EU) 2024/1772 (Arts. 6, 8 and 9). Returns the decision, which criteria are met, and the reporting time limits if major. Leave out what you do not know.

Use to assess how ready a financial entity is for DORA, or to find its gaps. Call without answers to get the 39 questions in five pillars (ICT risk management, incident management, resilience testing, ICT third-party risk, information sharing), each with its DORA article. Call with answers (yes, partial, no per question id) to get a score per pillar, an overall readiness level and the gaps.

Use after dora_gap_assessment when the user wants a plan to close their DORA gaps. Turns the same answers into every gap with a recommended action, a priority, the DORA article and a 30/60/90-day roadmap (ICT risk management and incident management first). Requires ClevSec Pro.

Use when a personal data breach has happened (data lost, stolen, sent to the wrong person, encrypted by ransomware, accessed without authorisation) to decide whether the GDPR requires notifying the supervisory authority within 72 hours (Art. 33) and the people affected (Art. 34), applying the exceptions. Needs the risk level of the breach: unlikely, risk or high.

Use to check how far an organisation is with GDPR compliance, or to list what GDPR requires in practice. Call without input to get the 48 checklist items in 8 areas (lawfulness, transparency and rights, minimisation and retention, security, breaches, processors, accountability, international transfers), each with its article. Call with the ids done (and optional items not applicable) to get the completion score and the open items.

Use after gdpr_dpia_screening when the user needs the DPIA worked out: a risk register linking each high or medium risk to its measures with coverage and indicative residual risk, and every gap (legal basis, special category data, necessity, missing measures, transfers, prior consultation under Art. 36) with an action, priority, article and a 30/60/90-day roadmap. Requires ClevSec Pro.

Use when someone plans new processing of personal data (a new system, AI use, monitoring, profiling) and asks whether a data protection impact assessment is required or how risky it is. Applies GDPR Art. 35(3), national lists and the nine WP248 rev.01 criteria, scores necessity and mitigation, and gives an indicative residual risk. Call without input to get the questions; every input is optional.

Use for 'how big could a GDPR fine be?' or 'how are GDPR fines calculated?'. Applies step 2 of the EDPB Guidelines 04/2022 method: the Art. 83(4) or 83(5) legal maximum, the starting amount band for the seriousness of the infringement, and the turnover adjustment. Give the seriousness, or the facts to let ClevSec suggest it. Returns a starting range in EUR, not a prediction of a real fine.

Use after gdpr_checklist_assessment when the user wants a plan to close their GDPR gaps. Turns the same input into every open item with a recommended action, a priority, the GDPR article and a 30/60/90-day roadmap (lawfulness, records, breach handling and processor contracts first). Requires ClevSec Pro.

Use to check how close an organisation is to ISO/IEC 27001:2022 certification, or to list the Annex A controls in practice. Call without answers to get 41 control checks in four themes (organizational, people, physical, technological) with their Annex A references. Call with a status per control (implemented, partial, planned, not_impl) to get a score per theme, a readiness level and the gaps.

Use after iso27001_gap_assessment when the user wants a plan towards ISO/IEC 27001 certification. Turns the same statuses into every gap with a recommended action, a priority, the Annex A control and a 30/60/90-day roadmap (organizational controls first). Requires ClevSec Pro.

Use to measure an organisation's cybersecurity maturity or to benchmark it against NIST CSF 2.0. Call without answers to get 39 capabilities in the six CSF functions and the 1-5 levels. Call with a level per capability to get the average per function and an overall maturity level.

Use after maturity_assessment when the user wants to raise their maturity. Lists every capability below the target level (3 or 4) with the next action, NIST CSF 2.0 subcategory, NIS2 article and a 30/60/90-day roadmap (govern and identify first). Requires ClevSec Pro.

Use before enabling an MCP server or connecting to an A2A agent ('is this MCP server safe to add?', 'check these tool descriptions'). Pass the server's tools/list response or the agent's Agent Card as document. Returns flags for hidden or manipulative text in descriptions (tool poisoning), risky capabilities (running code, sending data out, an exfiltration path), annotations that do not match, secrets in parameters and missing Agent Card security fields, with a level per tool and a SHA-256 fingerprint to detect later changes. Reads declared metadata only; it does not connect to the server.

Use after mcp_tools_check when the user wants a review report or to see what changed since approval. Pass document (current tools/list response or Agent Card) and optionally previous (the approved version). Returns every flag with an action, a priority, OWASP and MCP Security Audit Kit references, a change comparison (added, removed and changed tools with the changed fields) and an inventory row. Requires ClevSec Pro.

Use to assess how ready an organisation is for NIS2 cybersecurity requirements, or to find its gaps. Call without answers to get the 53 questions in nine domains (governance, risk, incidents, continuity, supply chain, network security, vulnerabilities, training, cryptography), each mapped to NIS2 Arts. 20, 21 or 23. Call with answers (yes, partial, no per question id) to get a score per domain, an overall readiness level and the gaps.

Use after nis2_gap_assessment when the user wants a plan to close their NIS2 gaps. Turns the same answers into every gap with a recommended action, a priority, the NIS2 article and a 30/60/90-day roadmap (governance, risk and incident gaps first). Requires ClevSec Pro.

Use for questions like 'does NIS2 apply to my company?', 'are we an essential or important entity?' or 'is a company of this size and sector in scope?'. Indicates whether the NIS2 Directive applies to an organisation and in which category (essential or important), from its sector, size and type, applying Arts. 2 and 3 of Directive (EU) 2022/2555 and the size rule of Recommendation 2003/361/EC. An indication only: national law and the member state's list decide.

Use when writing or checking a privacy policy or privacy notice. Lists every item the GDPR requires with its article, for data collected from the person (Art. 13) or obtained from other sources (Art. 14), when the notice must be given, and the exceptions. Tell it which situations apply to drop items you do not need.

Use for any question about incident or breach reporting deadlines in the EU (for example 'how long do we have to report a breach / a cyber incident?'). Lists who must report what, to whom and by when under GDPR (personal data breaches), NIS2 (significant incidents), DORA (major ICT-related incidents at financial entities) and the Cyber Resilience Act (actively exploited vulnerabilities and severe incidents), with the article for each deadline and when the clock starts.

Use after vendor_risk_assessment when the user needs to act on a vendor's gaps. Returns every gap with an action, the evidence to request from the vendor, ISO 27001 / GDPR / NIS2 / DORA references and a roadmap (before signing first), plus the contract clauses to include (GDPR Art. 28, NIS2 Art. 21, DORA Art. 30 when they apply). Requires ClevSec Pro.

Use when an organisation evaluates a supplier, SaaS or ICT provider (vendor due diligence, third-party risk, supply chain security under NIS2 Art. 21(2)(d) or DORA). Call without input to get the questions. Call with the vendor profile (type, criticality, data access, regimes) and answers (yes, partial, no, unknown) to get a risk score, risk level, monitoring tier and the gaps.