io.github.CSOAI-ORG/iso-27001-ai-mcp

Audit an Information Security Management System against ISO 27001:2022 Annex A controls (93 controls across 4 themes: Organizational, People, Physical, Technological). Returns compliance status per theme with gap identification and remediation priorities. Args: organization_context: Description of the organization, its AI systems, and ISMS scope scope_description: Specific scope of the ISMS audit (which systems, processes, locations) controls_implemented: List of Annex A control IDs already implemented (e.g. ["A.5.1", "A.8.24"]) 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 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.

Perform information security risk assessment per ISO 27005 methodology. Identifies threats, assesses likelihood and impact, calculates risk levels, and recommends treatment options with specific ISO 27001 Annex A controls. Args: system_description: Description of the AI system or information asset being assessed assets: List of information assets to assess (e.g. ["training data", "ML model", "API keys"]) threat_scenarios: Specific threat scenarios to evaluate (or auto-generated if omitted) existing_controls: Currently implemented controls that reduce risk 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 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.

Compare current controls to ISO 27001:2022 requirements and identify gaps. Provides prioritized remediation roadmap with effort estimates. Args: current_controls: List of currently implemented Annex A control IDs target_certification: Target level - "full" (all 93), "core" (critical subset), or "ai-focused" (AI-relevant controls) focus_themes: Optional filter to specific themes ["A.5", "A.6", "A.7", "A.8"] 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 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.

Map ISO 27001 controls to AI-specific requirements via ISO 42001 bridge. Shows how existing ISMS controls extend to AI governance, identifying where additional AI-specific controls are needed. Args: controls: Specific ISO 27001 controls to map (or all mapped controls if omitted) focus_area: Focus on "all", "data_protection", "model_security", "supply_chain", or "incident_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 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.

Generate a Statement of Applicability (SoA) per ISO 27001:2022 clause 6.1.3(d). The SoA documents which Annex A controls are applicable, implemented, excluded, and the justification for exclusions. Required for ISO 27001 certification. Args: organization_name: Name of the organization controls_implemented: List of implemented Annex A control IDs controls_excluded: Controls deliberately excluded with justification exclusion_justifications: Dict mapping excluded control IDs to justification text 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 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.

Classify security incidents per ISO 27001 incident management framework (controls A.5.24-A.5.28). Determines severity, notification requirements, response procedures, and evidence collection needs. Includes AI-specific incident classification when AI systems are involved. Args: incident_description: Description of the security incident affected_assets: List of affected information assets detection_method: How the incident was detected (automated/manual/third-party/user-report) data_breach: Whether personal data was compromised ai_system_involved: Whether an AI system was involved in or affected by the incident 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 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.