Categories › AI & Agents › Thinking, planning & prompt tools
Live URL scan, AI Act risk check, 24-EU-language Art. 50 badge, HMAC receipts & approval gates.
Remote server: your requests and data go to console.spurvik.com. Claude Code: claude mcp add --transport http spurvik-eu-ai-act https://console.spurvik.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
spurvik_setup_snippet — Return a setup snippet for openai, anthropic, google-genai, vercel-ai-sdk, mastra, openai-agents, or langgraph. Provider clients are wrappedspurvik_find_unwrapped_calls — Heuristic static scan of one directory inside the workspace root for AI client calls that are not passed through withSpurvik, spurvikMiddlewspurvik_explain_receipt — Explain the fields of an HMAC provenance receipt JSON. If signingSecret is passed, or SPURVIK_SIGNING_SECRET is set, check the HMAC locally spurvik_marking_hooks — Explain how to plug your own Article 50(2) marking into marking.text or marking.media. Spurvik does not mark content. withSpurvik and spurvispurvik_scan_live_url — Scan one public HTTPS page for AI chat widgets and AI SDKs and check whether a visible EU AI Act Article 50(1) notice is present. Returns thspurvik_classify_ai_act_risk — Self-assessment of an AI system under the EU AI Act from a few answers: prohibited (Article 5), high-risk (Annex III), Article 50 transparenspurvik_generate_art50_badge — Generate a copy-paste EU AI Act Article 50 notice: a badge.js <script> tag or a React <AIDisclosureLabel /> snippet, in any of the 24 EU lanNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.