ClevSec MCP server
Which servers in the official MCP registry are ClevSec's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry nameone.clevsec/eu-complianceverified in the MCP registry
The registry name sits under clevsec.one. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools9
- Server calls itselfclevsec
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 184 ms.
- Its tools do check NIS2 readiness across control domains, but not draft an ISO 27001 statement of applicability; prepare a board briefing on NIS2 management liability.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- For "check NIS2 readiness across control domains", the likely first call is nis2_gap_assessment.
- Parameters are untyped or undescribed in 7 of 28 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it1 of 3 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer2051 ms
- Space in an agent's context≈ 13,093 tokensthe definitions of all its tools (28), which an agent carries on every turn
- Tool definitionsA · 96 of 100
- Typed results0 of 28 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 7 of 28
What an agent can do with it
- can do · check NIS2 readiness across control domains
- cannot · draft an ISO 27001 statement of applicability
- cannot · prepare a board briefing on NIS2 management liability
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
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?'). Lists who must report what, to whom and by when under GDPR (personal data breaches)…
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?'. Indicates whether the NIS2 Directive applies to an organisation and in which category…
nis2_gap_assessmentUse 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…
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 reported under DORA. Classifies the ICT-related incident as…
dora_checklistUse 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…
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 requires notifying the supervisory authority within 72 hours…
gdpr_fine_estimateUse 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…
privacy_notice_requirementsUse 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…
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. Applies Art. 14 of the Cyber Resilience Act (Regulation (EU) 2024/2847), in force since 11…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"eu-compliance": {
"type": "http",
"url": "https://mcp.clevsec.one/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http clevsec https://mcp.clevsec.one/mcpclaude.ai, ChatGPT and other clients: add https://mcp.clevsec.one/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.