ClevSec EU compliance tools MCP server
one.clevsec/eu-complianceclevsec.onestreamable-httpv1.5.0Scanned
Deterministic, sourced EU compliance checks: NIS2, DORA, GDPR, Cyber Resilience Act and AI Act.
32 tools: 32 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
32 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ClevSec EU compliance tools MCP server can do
The ClevSec EU compliance tools MCP server is published by clevsec.one, a domain the MCP Registry verified. It has 32 tools. It can create or change data (32 tools: reporting_deadlines, nis2_scope_check, nis2_gap_assessment, dora_classify_incident and 28 more), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
32 tools
Changes things 32Claude Code: ask
agent_risk_checkUse 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?').No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
ai_act_scope_checkUse 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 appl…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cookie_consent_checkUse when someone asks whether their cookie banner or cookie consent is compliant in the EU (ePrivacy Art.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cookie_consent_fix_planUse after cookie_consent_check when the user wants to fix their cookie consent.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cra_reporting_checkUse when a manufacturer of hardware or software sold in the EU learns of an actively exploited vulnerability or a security incident in its product.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cyber_risk_action_planUse after cyber_risk_score when the user wants to reduce their risk.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cyber_risk_scoreUse for a quick view of a small organisation's cyber risk ('how secure are we?', 'what is our cyber risk score?').No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
data_flow_record_checkUse when someone maps personal data flows or builds GDPR records of processing activities (ROPA, Art.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
data_flow_reviewUse 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, ret…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dora_checklistUse for 'what does DORA require?', DORA compliance checklists or gap reviews.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dora_classify_incidentUse 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 report…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dora_gap_assessmentUse to assess how ready a financial entity is for DORA, or to find its gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
dora_remediation_planUse after dora_gap_assessment when the user wants a plan to close their DORA gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_breach_decisionUse 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 requi…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_checklist_assessmentUse to check how far an organisation is with GDPR compliance, or to list what GDPR requires in practice.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_dpia_reportUse 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, …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_dpia_screeningUse 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 i…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_fine_estimateUse for 'how big could a GDPR fine be?' or 'how are GDPR fines calculated?'.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gdpr_remediation_planUse after gdpr_checklist_assessment when the user wants a plan to close their GDPR gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
iso27001_gap_assessmentUse to check how close an organisation is to ISO/IEC 27001:2022 certification, or to list the Annex A controls in practice.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
iso27001_remediation_planUse after iso27001_gap_assessment when the user wants a plan towards ISO/IEC 27001 certification.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
maturity_assessmentUse to measure an organisation's cybersecurity maturity or to benchmark it against NIST CSF 2.0.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
maturity_improvement_planUse after maturity_assessment when the user wants to raise their maturity.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mcp_tools_checkUse before enabling an MCP server or connecting to an A2A agent ('is this MCP server safe to add?', 'check these tool descriptions').No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mcp_tools_reportUse after mcp_tools_check when the user wants a review report or to see what changed since approval.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
nis2_gap_assessmentUse to assess how ready an organisation is for NIS2 cybersecurity requirements, or to find its gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
nis2_remediation_planUse after nis2_gap_assessment when the user wants a plan to close their NIS2 gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
nis2_scope_checkUse 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?'.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
privacy_notice_requirementsUse when writing or checking a privacy policy or privacy notice.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
reporting_deadlinesUse 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?').No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vendor_due_diligence_planUse after vendor_risk_assessment when the user needs to act on a vendor's gaps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vendor_risk_assessmentUse when an organisation evaluates a supplier, SaaS or ICT provider (vendor due diligence, third-party risk, supply chain security under NIS2 Art.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:16 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 32
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 32 tools that change things (32 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.clevsec.one/mcp: tools/list returned 32 tools to an anonymous client, including reporting_deadlines (write), nis2_scope_check (write), nis2_gap_assessment (write), dora_classify_incident (write), dora_checklist (write) and 27 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 31 to 32
- Nov 6, 2026
- Tools that change things, listed without credentials: 28 to 31
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 31 -> 32.View diff
- Tools that change things, listed without credentials: 31 to 32
Tools1 added.+1 addedView diff
- Added:ai_act_scope_checkChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 28 -> 31.View diff
- Tools that change things, listed without credentials: 28 to 31
Tools2 added.+2 addedView diff
- Added:mcp_tools_checkChanges things
- Added:mcp_tools_reportChanges things
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:agent_risk_checkChanges things
- Changed:gdpr_checklist_assessmentChanges thingsdescription
Install
Pinned to version 1.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http eu-compliance https://mcp.clevsec.one/mcpclaude mcp add --transport http eu-compliance https://mcp.clevsec.one/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__eu-compliance__reporting_deadlines",
"mcp__eu-compliance__nis2_scope_check",
"mcp__eu-compliance__nis2_gap_assessment",
"mcp__eu-compliance__dora_classify_incident",
"mcp__eu-compliance__dora_checklist",
"mcp__eu-compliance__dora_gap_assessment",
"mcp__eu-compliance__gdpr_breach_decision",
"mcp__eu-compliance__gdpr_fine_estimate",
"mcp__eu-compliance__gdpr_checklist_assessment",
"mcp__eu-compliance__gdpr_dpia_screening",
"mcp__eu-compliance__privacy_notice_requirements",
"mcp__eu-compliance__data_flow_record_check",
"mcp__eu-compliance__cookie_consent_check",
"mcp__eu-compliance__cra_reporting_check",
"mcp__eu-compliance__iso27001_gap_assessment",
"mcp__eu-compliance__vendor_risk_assessment",
"mcp__eu-compliance__maturity_assessment",
"mcp__eu-compliance__cyber_risk_score",
"mcp__eu-compliance__agent_risk_check",
"mcp__eu-compliance__mcp_tools_check",
"mcp__eu-compliance__ai_act_scope_check",
"mcp__eu-compliance__nis2_remediation_plan",
"mcp__eu-compliance__dora_remediation_plan",
"mcp__eu-compliance__gdpr_remediation_plan",
"mcp__eu-compliance__gdpr_dpia_report",
"mcp__eu-compliance__data_flow_review",
"mcp__eu-compliance__cookie_consent_fix_plan",
"mcp__eu-compliance__iso27001_remediation_plan",
"mcp__eu-compliance__vendor_due_diligence_plan",
"mcp__eu-compliance__maturity_improvement_plan",
"mcp__eu-compliance__cyber_risk_action_plan",
"mcp__eu-compliance__mcp_tools_report"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as eu-compliance. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/one.clevsec/eu-compliance/verify?hash=b869c391f42b10c74c07fd8144d953708099db47dcc107d7217e97c6aebce04d" | jq -e '.changed == false'Pinned hash b869c391f42b, from Nov 10, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/one.clevsec/eu-compliance/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/one.clevsec/eu-compliance)Source: MCP Registry. Synced Nov 10, 2026, 13:18 UTC.
ClevSec EU compliance tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ClevSec EU compliance tools MCP server safe?
- No scan can promise that. What its definitions show: 32 tools, 32 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ClevSec EU compliance tools MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ClevSec EU compliance tools MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ClevSec EU compliance tools MCP server have?
- 32 tools: 32 write. reporting_deadlines, nis2_scope_check, nis2_gap_assessment, dora_classify_incident, dora_checklist, dora_gap_assessment, gdpr_breach_decision, gdpr_fine_estimate and 24 more.
Does the ClevSec EU compliance tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ClevSec EU compliance tools MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ClevSec EU compliance tools MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.