About conformy
EU AI Act & NIS2 compliance: classify AI systems, check obligations, draft docs
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
17Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| role | enum | Yes | Your role: 'provider' if you build/develop/train the AI system, 'deployer' if you use/deploy it in your organisationprovider | deployer |
| language | enum | No | Response language: 'sv' (Swedish) or 'en' (English). Default: 'en'sv | en |
| annex_iii_category | enum | No | High-risk category under Annex III, if known. See list_annex_iii_categories for descriptions.none | biometrics | criticalInfrastructure | educationAndVocationalTraining | employmentAndWorkersManagement | essentialServices | lawEnforcement | migrationAsylumBorderControl | justiceAndDemocracy |
| performs_profiling | boolean | No | Does the system profile natural persons based on personal data? |
| system_description | string | Yes | Description of the AI system — what it does, how it works, what decisions it makes or influences |
| prohibited_practices | object | No | Article 5 prohibited practice checks. If any are true, the system is classified as prohibited. |
| prohibited_practices.social_scoring | boolean | No | Social scoring by public authorities leading to detrimental treatment |
| prohibited_practices.facial_image_scraping | boolean | No | Creates or expands facial recognition databases through untargeted scraping |
| prohibited_practices.real_time_biometric_id | boolean | No | Real-time remote biometric identification in publicly accessible spaces for law enforcement |
| prohibited_practices.criminal_risk_profiling | boolean | No | Assesses risk of criminal offences based solely on profiling or personality traits |
| prohibited_practices.subliminal_manipulation | boolean | No | Uses subliminal techniques to materially distort behaviour, causing significant harm |
| prohibited_practices.biometric_categorization | boolean | No | Categorises individuals based on biometric data to infer sensitive attributes (race, political opinions, etc.) |
| prohibited_practices.exploits_vulnerabilities | boolean | No | Exploits vulnerabilities of a specific group (age, disability, social/economic situation) |
| prohibited_practices.workplace_emotion_inference | boolean | No | Infers emotions in the workplace or educational institutions |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.