io.github.CSOAI-ORG/canada-aida-ai-mcp

Classify an AI system under AIDA as high-impact or general-purpose. Evaluates against high-impact criteria including health/safety, human rights, economic impact, vulnerable populations, and bias risk. Args: system_description: Description of the AI system system_purpose: Primary purpose of the AI system target_users: Who uses or is affected by the system (e.g. ["patients", "employees", "children"]) data_types: Types of data the system processes (e.g. ["personal", "health", "biometric"]) deployment_context: Context of deployment: "commercial", "government", "healthcare", "finance", "education" interprovincial_trade: Whether the system operates in interprovincial or international trade (AIDA scope) caller: Caller identifier for rate limiting tier: Access tier (free/pro) 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 structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Perform an AI impact assessment per AIDA requirements (Sections 7-8). Evaluates potential harms, biased output risks, and required mitigation measures for high-impact AI systems. Args: system_name: Name of the AI system system_description: Detailed description of the system and its function affected_populations: Groups of people affected by the system risk_scenarios: Specific risk scenarios to evaluate mitigation_measures: Currently implemented mitigation measures caller: Caller identifier for rate limiting tier: Access tier (free/pro) 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 structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. 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.

Check compliance with AIDA obligations. Evaluates whether a responsible person meets all AIDA requirements for their AI system classification. Args: system_classification: Classification result: "HIGH_IMPACT" or "GENERAL" measures_in_place: List of compliance measures implemented records_maintained: Whether Section 9 records are being kept public_description_published: Whether Section 10 public description is published monitoring_active: Whether Section 8 monitoring is in place notification_procedures: Whether Sections 11-12 notification procedures exist caller: Caller identifier for rate limiting tier: Access tier (free/pro) 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 structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Map AIDA requirements to EU AI Act obligations. Essential for organizations operating in both Canadian and European markets, showing where compliance overlaps and where additional measures are needed. Args: focus_area: Focus on "all", "classification", "transparency", "enforcement", or "risk_management" caller: Caller identifier for rate limiting tier: Access tier (free/pro) 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 structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Generate AIDA compliance documentation including public system descriptions (Section 10), compliance records (Section 9), and notification templates (Sections 11-12). Args: system_name: Name of the AI system system_description: Description of the AI system classification: AIDA classification: "HIGH_IMPACT" or "GENERAL" responsible_person: Name/org of the responsible person under AIDA document_type: Type of document: "public_description", "compliance_record", "notification_affected", "notification_minister" caller: Caller identifier for rate limiting tier: Access tier (free/pro) Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.