multi_jurisdiction_map
Map EU AI Act requirements to equivalent regulations in the UK, Singapore, Canada, and US NIST for cross-jurisdiction compliance analysis.
Instructions
Map EU AI Act articles to equivalent requirements in UK, Singapore, Canada, and US NIST.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.
When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| article | Yes | ||
| jurisdictions | No | ||
| api_key | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- server.py:1778-1830 (handler)Handler function for the multi_jurisdiction_map MCP tool. Maps EU AI Act articles (Article 5, 6, 9, 14) to equivalent requirements in UK, Singapore, Canada, and US NIST frameworks. Returns a dictionary with article, mappings, and jurisdictions queried.
@mcp.tool() def multi_jurisdiction_map( article: str, jurisdictions: list = None, api_key: str = "") -> str: """Map EU AI Act articles to equivalent requirements in UK, Singapore, Canada, and US NIST. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process. """ allowed, msg, tier = check_access(api_key) if not allowed: return {"error": msg, "upgrade_url": "https://meok.ai/pricing"} limit_err = _check_rate_limit("anonymous", tier) if limit_err: return {"error": "rate_limited", "message": limit_err} jurisdictions = jurisdictions or ["uk", "singapore", "canada", "us_nist"] MAPPINGS = { "Article 5": {"uk": "UK AI Act prohibited practices", "singapore": "MAS FEAT principles — fairness", "canada": "AIDA prohibited uses", "us_nist": "NIST AI RMF Govern 1.1"}, "Article 6": {"uk": "UK AI Act high-risk classification", "singapore": "IMDA PDPC guidelines", "canada": "AIDA high-impact systems", "us_nist": "NIST AI RMF Map 1.2"}, "Article 9": {"uk": "UK AI Act risk management", "singapore": "Veritas fairness assessment", "canada": "AIDA risk mitigation", "us_nist": "NIST AI RMF Manage 2.1"}, "Article 14": {"uk": "UK AI Act human oversight", "singapore": "AI Governance Framework — human-in-the-loop", "canada": "AIDA human oversight", "us_nist": "NIST AI RMF Govern 3.1"}, } result = MAPPINGS.get(article, {}) filtered = {k: v for k, v in result.items() if k in jurisdictions} return {"eu_ai_act_article": article, "mappings": filtered, "jurisdictions_queried": jurisdictions} - server.py:1778-1778 (registration)Tool registration via the @mcp.tool() decorator on the FastMCP instance 'mcp'.
@mcp.tool() - server.py:659-665 (helper)JURISDICTIONS constant defining metadata for each supported jurisdiction (EU, UK, Canada, Singapore, US NIST) — used as supporting data for multi-jurisdiction functionality.
JURISDICTIONS = { "eu": {"name": "European Union", "framework": "EU AI Act (Regulation 2024/1689)", "enforcement": "August 2, 2026", "penalty_max": "EUR 35M or 7% global turnover"}, "uk": {"name": "United Kingdom", "framework": "UK AI Act (expected mid-2026)", "enforcement": "TBD — legislation pending", "penalty_max": "TBD"}, "canada": {"name": "Canada", "framework": "AIDA (Artificial Intelligence and Data Act)", "enforcement": "Expected 2026", "penalty_max": "CAD 25M or 5% global revenue"}, "singapore": {"name": "Singapore", "framework": "AI Governance Framework + Agentic AI", "enforcement": "Voluntary (mandatory for financial services)", "penalty_max": "Sector-specific"}, "us_nist": {"name": "United States (NIST)", "framework": "NIST AI RMF 1.0", "enforcement": "Voluntary (mandatory for federal agencies)", "penalty_max": "N/A (framework, not law)"}, }