Get real service health status by querying each subsystem.

Get cache statistics.

List all available AI governance frameworks from the FINOS repository.

Use this tool to discover what AI governance frameworks are available for analysis, compliance checking, or reference. This is typically the first step when helping users understand regulatory requirements or compliance gaps.

Examples of available frameworks (call this tool for the full, current list):

• NIST AI 600-1 (US federal AI governance)

• EU AI Act (European Union AI regulation)

• ISO 42001 (international AI management standard)

• OWASP LLM Top 10 (AI security best practices)

• OWASP ML Security Top 10 (machine learning security best practices)

Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.

Get the complete content of a specific AI governance framework.

Use this tool to retrieve detailed framework content for compliance analysis, requirement extraction, or regulatory guidance. The content includes structured requirements, controls, and implementation guidance.

List all available AI governance risk documents for threat assessment and security planning.

Use this tool to discover security risks, privacy threats, and compliance vulnerabilities in AI systems. Each risk document provides detailed threat analysis, impact assessment, and contextual information for risk management decisions.

Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.

List all available AI governance mitigation strategies for risk reduction and security controls.

Use this tool to discover security controls, privacy safeguards, and compliance measures for AI systems. Each mitigation document provides actionable controls, implementation guidance, and best practices for reducing identified risks and threats.

Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.

Get the complete content of a specific AI governance risk document for detailed threat analysis.

Use this tool to retrieve comprehensive risk information including threat descriptions, impact assessments, likelihood analysis, and contextual details. Essential for security assessments, compliance audits, and risk management planning.

Get the complete content of a specific AI governance mitigation strategy for risk control implementation.

Use this tool to retrieve detailed mitigation instructions including security controls, implementation steps, monitoring procedures, and effectiveness measures. Critical for security implementation, compliance remediation, and risk reduction planning.

Find an exact phrase in the text of the AI governance frameworks.

Frameworks only: this tool does not search risks or mitigations. To find a risk or a mitigation, call list_risks or list_mitigations, choose from the titles and descriptions, then read it with get_risk or get_mitigation.

The query is matched as one phrase of whole words. Case is ignored, and hyphens and underscores count as spaces, so "third party" finds "third-party". Words of the query that appear apart are not a match, and neither is a word inside a longer one. Link addresses are not searched.

Returns one result per framework that says the phrase, in the order list_frameworks gives them. Results are not ranked. Each has the framework's document_id (pass it to get_framework), the section and passage around the first occurrence, and occurrences, the number of times that framework says the phrase. If nothing is found, no framework says that phrase: try a shorter phrase or a single word.

A search that could not run is an error, not an empty result. A framework that cannot be read is left out, and the search fails if none can be read.