ark-forge/mcp-eu-ai-act

One command. Zero config. Full EU AI Act + GDPR compliance report in under 10 seconds.
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.
**August 2, 2026 enforcement deadline. Fines up to 35M EUR or 7% global turnover.**
If this tool helps your compliance work, a ⭐ on GitHub helps others discover it.
> **Need audit-grade proof?** Certify every scan with ArkForge Trust Layer — tamper-proof, timestamped compliance evidence. 500 free proofs/month.
**Get your compliance report →**
Quick Start
CLI (scan any project in 10 seconds)
Output:
Or specify a path directly: eu-ai-act-scanner /path/to/your/project
Track compliance over time (free): eu-ai-act-scanner . --register you@email.com
Free vs Pro
| | Free | Pro (€29/mo) | Certified (€99/mo) |
|--|------|--------------|---------------------|
| **Scans per day** | 5 | Unlimited | Unlimited |
| **AI framework detection** | ✓ (16 frameworks) | ✓ (16 frameworks) | ✓ (16 frameworks) |
| **Risk category suggestion** | ✓ | ✓ | ✓ |
| **Compliance check** | — | ✓ (content scoring 0-100) | ✓ |
| **Full compliance report** | — | ✓ (executive + technical) | ✓ |
| **Compliance roadmap** | — | ✓ (week-by-week plan) | ✓ |
| **Annex IV package** | — | ✓ (auditor-ready ZIP) | ✓ |
| **GDPR scan** | — | ✓ | ✓ |
| **Combined EU AI Act + GDPR** | — | ✓ (dual-compliance hotspots) | ✓ |
| **Trust Layer certification** | — | — | ✓ (cryptographic proof) |
| **CI/CD integration** | — | ✓ | ✓ |
| **API key** | Not required | ✓ | ✓ |
| **Tools available** | 2 | 10 | 10 + certification |
Free tier: no sign-up, no API key — just pip install and scan. Pro unlocks the full compliance toolkit your team needs before the August 2027 deadline.
**→ Compare plans & get your API key**
What's New in v2
| Feature | Description |
|---------|-------------|
| generate_compliance_roadmap | Week-by-week action plan to reach compliance before your deadline |
| generate_annex4_package | Auditor-ready ZIP with all 8 Annex IV sections populated from your code |
| certify_compliance_report | Cryptographic proof via Trust Layer (EU AI Act Art. 12) |
| Content scoring | check_compliance now scores document *content* (0-100), not just existence |
| Article mapping | Every finding mapped to specific EU AI Act article |
MCP Server (from source)
Run tests
MCP Integration
Install from PyPI (recommended)
Claude Code
Claude Desktop
Add to claude_desktop_config.json:
Cursor
Add to .cursor/mcp.json:
HTTP mode (for CI/CD or remote clients)
Tools Reference
1. scan_project
Detects AI framework usage in source code and config/manifest files. Supports 16 frameworks across Python, JS, TS, Go, Java, and Rust.
**Key parameters:** project_path (string, required)
**Example output:**
---
2. check_compliance
Scores document *content* quality (0-100) and maps each finding to a specific EU AI Act article. Score ≥40 = pass. Fully backward compatible with v1.
**Key parameters:** project_path (string, required), risk_category (string, default: limited)
**Example output (v2):**
---
3. generate_compliance_roadmap — NEW in v2
Deadline-aware, week-by-week action plan to reach EU AI Act compliance before August 2, 2026. Sequences quick wins first using a criticality × 1/effort algorithm.
**Key parameters:** project_path (string, required), risk_category (string), target_date (string, ISO format, default: 2027-08-02)
**Example output:**
---
4. generate_report
Runs scan + compliance check, returns a combined report with two-level output: executive summary for DPO/legal and technical breakdown for developers. Article-by-article citations included.
**Key parameters:** project_path (string, required), risk_category (string, default: limited)