Mcp Eu Ai Act

ark-forge/mcp-eu-ai-act

Exposes a single-call EU AI Act and GDPR compliance scanner that runs in about 10 seconds with no arguments required. Detects 22 AI frameworks across Python, JavaScript, TypeScript, Go, Java, and Rust codebases, maps findings to specific legal articles, and returns pass/fail results with remediation steps. The free tier works without an API key and gives you basic framework detection and risk categorization. Pro tier adds content scoring (0-100 scale), week-by-week compliance roadmaps, and Annex IV audit packages. Useful when you need to quickly assess compliance posture in Claude or Cursor before the August 2026 enforcement deadline, or integrate compliance checks into CI/CD pipelines via the HTTP transport mode.

GitHub stars: 8
tools: 16
transport: HTTP
last updated: Apr 24, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://mcp.arkforge.tech/mcp --name mcp-eu-ai-act

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http mcp-eu-ai-act https://mcp.arkforge.tech/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 16 tools

Verified live against the running server on Nov 6, 2026.

scan_projectFind out in 5 seconds if your project triggers EU AI Act obligations — no arguments, no setup. Scans for 22 AI/ML frameworks (OpenAI, Anthropic, LangChain, HuggingFace, PyTorch, TensorFlow, scikit-learn…), returns your risk category and the legal actions required before you sh...2 params

Find out in 5 seconds if your project triggers EU AI Act obligations — no arguments, no setup. Scans for 22 AI/ML frameworks (OpenAI, Anthropic, LangChain, HuggingFace, PyTorch, TensorFlow, scikit-learn…), returns your risk category and the legal actions required before you sh...

Parameters* required

follow_importsboolean

When true, also flag files that transitively import AI-flagged modules. Default false is fine for most projects.default: false

project_pathstring

Path to the project root. Omit entirely or pass '.' to scan the current working directory — no path discovery needed.default: .

check_complianceCheck whether your project passes or fails each EU AI Act requirement — no arguments, 5 seconds. See exactly which articles you violate (Art. 52 transparency, Art. 11 documentation, Art. 14 human oversight, Art. 15 robustness) and get step-by-step fix instructions for every ga...2 params

Check whether your project passes or fails each EU AI Act requirement — no arguments, 5 seconds. See exactly which articles you violate (Art. 52 transparency, Art. 11 documentation, Art. 14 human oversight, Art. 15 robustness) and get step-by-step fix instructions for every ga...

Parameters* required

project_pathstring

Path to the project root. Omit entirely or pass '.' to check the current working directory.default: .

risk_categoryvalue

EU AI Act risk category: 'minimal', 'limited' (default, fits most AI apps), 'high', or 'unacceptable'.default: limited

generate_reportGenerate the compliance report your legal team is asking for — no arguments. One call auto-detects AI frameworks, runs gap analysis, and produces a structured remediation plan ready for legal review or DPIA attachment. No API key needed.2 params

Generate the compliance report your legal team is asking for — no arguments. One call auto-detects AI frameworks, runs gap analysis, and produces a structured remediation plan ready for legal review or DPIA attachment. No API key needed.

Parameters* required

project_pathstring

Path to the project root. Omit entirely or pass '.' to scan the current working directory.default: .

risk_categoryvalue

EU AI Act risk category: 'minimal', 'limited' (default), 'high', or 'unacceptable'.default: limited

suggest_risk_categoryDescribe what your AI system does in plain language — get back your EU AI Act risk tier, the articles that apply, and your first compliance step. Returns matched category (minimal/limited/high/unacceptable) with confidence level and triggering risk indicators. No project scan...1 params

Describe what your AI system does in plain language — get back your EU AI Act risk tier, the articles that apply, and your first compliance step. Returns matched category (minimal/limited/high/unacceptable) with confidence level and triggering risk indicators. No project scan...

Parameters* required

system_description*string

Short description of what the AI system does, e.g. 'chatbot for customer support' or 'CV screening tool for recruitment'.

generate_compliance_templatesStop writing compliance docs from scratch — get pre-filled templates for risk management, technical documentation, transparency notice, and human oversight policy tailored to your risk category. High-risk systems get all 6 mandatory documents. Save to docs/, fill in [bracketed...1 params

Stop writing compliance docs from scratch — get pre-filled templates for risk management, technical documentation, transparency notice, and human oversight policy tailored to your risk category. High-risk systems get all 6 mandatory documents. Save to docs/, fill in [bracketed...

Parameters* required

risk_categoryvalue

EU AI Act risk category. Templates are most useful for 'high' risk.default: high

generate_compliance_roadmapGet a prioritized, week-by-week plan to close every compliance gap before Aug 2027 — no arguments. Auto-scans your project, ranks fixes by impact, sequences quick wins first, tells you whether your deadline is achievable. Pro plan required — run check_compliance() for a free g...3 params

Get a prioritized, week-by-week plan to close every compliance gap before Aug 2027 — no arguments. Auto-scans your project, ranks fixes by impact, sequences quick wins first, tells you whether your deadline is achievable. Pro plan required — run check_compliance() for a free g...

Parameters* required

deadlinestring

Target compliance deadline in ISO format.default: 2027-08-02

project_pathstring

Path to the project root. Leave empty or pass '.' to scan the current directory.default: .

risk_categoryvalue

EU AI Act risk category.default: high

generate_annex4_packageBuild the Annex IV evidence package your auditor needs for high-risk AI — no arguments. All 8 mandatory sections auto-populated from your project scan, SHA-256 integrity hash included. High-risk rules apply Aug 2026. Pro plan required.3 params

Build the Annex IV evidence package your auditor needs for high-risk AI — no arguments. All 8 mandatory sections auto-populated from your project scan, SHA-256 integrity hash included. High-risk rules apply Aug 2026. Pro plan required.

Parameters* required

project_pathstring

Path to the project root. Leave empty or pass '.' to scan the current directory.default: .

sign_with_trust_layerboolean

Certify the package via Trust Layer for Art. 12 audit trail.default: false

trust_layer_keystring

ArkForge Trust Layer API key. Required if sign_with_trust_layer is True.default:

certify_compliance_reportMake your compliance report tamper-proof for Art. 12 audit trail — pass the report JSON, get back a proof_id and a public verification URL you can hand to auditors. Certified plan required. Run generate_report() first to produce the report.2 params

Make your compliance report tamper-proof for Art. 12 audit trail — pass the report JSON, get back a proof_id and a public verification URL you can hand to auditors. Certified plan required. Run generate_report() first to produce the report.

Parameters* required

report_data*string

JSON string of the compliance report to certify.

trust_layer_key*string

ArkForge Trust Layer API key.

validate_api_keyCheck your API key status — returns plan tier (free/pro/certified), email, and usage stats (total scans, last scan date).1 params

Check your API key status — returns plan tier (free/pro/certified), email, and usage stats (total scans, last scan date).

Parameters* required

api_key*string

The API key to validate.

register_free_keyActivate a free API key — unlocks scan history and CI/CD integration. Pass the user's email, no password or credit card. IMPORTANT: ask the user to type their email first, wait for their reply, then call this with the exact email they typed. Do NOT pass a placeholder or fabric...1 params

Activate a free API key — unlocks scan history and CI/CD integration. Pass the user's email, no password or credit card. IMPORTANT: ask the user to type their email first, wait for their reply, then call this with the exact email they typed. Do NOT pass a placeholder or fabric...

Parameters* required

email*string

The user's email address. MUST come from the user's message, not generated by the agent.

gdpr_scan_projectFind every file in your project that touches personal data — no arguments, 5 seconds, free. Detects PII fields, cookies, tracking pixels, analytics SDKs, and consent flows. Returns flagged files with data categories and applicable GDPR articles. GDPR fines reach 20M EUR or 4%...1 params

Find every file in your project that touches personal data — no arguments, 5 seconds, free. Detects PII fields, cookies, tracking pixels, analytics SDKs, and consent flows. Returns flagged files with data categories and applicable GDPR articles. GDPR fines reach 20M EUR or 4%...

Parameters* required

project_pathstring

Path to the project root. Leave empty or pass '.' to scan the current directory.default: .

gdpr_check_complianceCheck whether your project passes or fails each GDPR requirement — no arguments. See pass/fail for lawful basis (Art. 6), consent (Art. 7), data subject rights (Art. 15–22), security (Art. 32), and breach notification (Art. 33–34) with fix instructions for every gap. GDPR fine...2 params

Check whether your project passes or fails each GDPR requirement — no arguments. See pass/fail for lawful basis (Art. 6), consent (Art. 7), data subject rights (Art. 15–22), security (Art. 32), and breach notification (Art. 33–34) with fix instructions for every gap. GDPR fine...

Parameters* required

processing_rolevalue

GDPR role: controller, processor, or minimal_processing.default: controller

project_pathstring

Path to the project root. Leave empty or pass '.' to check the current directory.default: .

gdpr_generate_reportGenerate the GDPR report your DPO needs — no arguments. Combines personal data inventory, gap analysis, and remediation steps in one structured document for DPO review, audit prep, or regulatory response. For EU AI Act + GDPR together, call combined_compliance_report().2 params

Generate the GDPR report your DPO needs — no arguments. Combines personal data inventory, gap analysis, and remediation steps in one structured document for DPO review, audit prep, or regulatory response. For EU AI Act + GDPR together, call combined_compliance_report().

Parameters* required

processing_rolevalue

GDPR role: controller, processor, or minimal_processing.default: controller

project_pathstring

Path to the project root. Leave empty or pass '.' to scan the current directory.default: .

gdpr_generate_templatesGet pre-filled GDPR templates your organization actually needs — no arguments. Privacy Policy, DPIA, Records of Processing Activities (ROPA), and Data Breach Procedure tailored to your processing role. Fill in [bracketed] sections. Run gdpr_check_compliance() first to see whic...1 params

Get pre-filled GDPR templates your organization actually needs — no arguments. Privacy Policy, DPIA, Records of Processing Activities (ROPA), and Data Breach Procedure tailored to your processing role. Fill in [bracketed] sections. Run gdpr_check_compliance() first to see whic...

Parameters* required

processing_rolevalue

GDPR role: controller, processor, or minimal_processing.default: controller

combined_compliance_reportRun this before your next deploy. One call reveals every EU AI Act + GDPR gap in your codebase — no arguments, no setup, under 10 seconds, free. Detects AI frameworks and personal data flows, flags where both laws overlap, returns pass/fail per article with a prioritized fix l...3 params

Run this before your next deploy. One call reveals every EU AI Act + GDPR gap in your codebase — no arguments, no setup, under 10 seconds, free. Detects AI frameworks and personal data flows, flags where both laws overlap, returns pass/fail per article with a prioritized fix l...

Parameters* required

processing_rolevalue

GDPR processing role: 'controller' (default, most common), 'processor', or 'minimal_processing'.default: controller

project_pathstring

Path to the project root. Omit entirely or pass '.' to scan the current working directory — no arguments required.default: .

risk_categoryvalue

EU AI Act risk category: 'minimal', 'limited' (default, fits most AI apps), 'high', or 'unacceptable'.default: limited

get_pricingSee pricing and features for every plan — Free (10 scans/day, full reports), Pro (29 EUR/mo, unlimited + CI/CD), Certified (cryptographic audit trail). No arguments. Call register_free_key() to activate your free API key.

See pricing and features for every plan — Free (10 scans/day, full reports), Pro (29 EUR/mo, unlimited + CI/CD), Certified (cryptographic audit trail). No arguments. Call register_free_key() to activate your free API key.

No parameters. Call it with no arguments.

Readme

EU AI Act Compliance Scanner — CLI + MCP Server

One command. Zero config. Full EU AI Act + GDPR compliance report in under 10 seconds.

pip install eu-ai-act-scanner
eu-ai-act-scanner /path/to/your/project

Detects 16 AI frameworks in your codebase, maps each to binding legal articles, returns pass/fail with fix instructions. Free tier, no API key needed.

View the full README on GitHub

Details

Repository: github.com/ark-forge/mcp-eu-ai-act
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026