GIA Governance

AI workforce governance control plane.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

Classify Decision: Classify an AI agent decision using the MAI Framework (Mandatory/Advisory/Informational). Returns classification level, confidence score, gate requirements, and rationale.
Evaluate Threshold: Compute the Storey Threshold — escalation rate (gates required / total operations). Returns current rate, status, and recommendations. Healthy band 10-18% is a design heuristic, no
Score Governance: Compute weighted governance score from caller-provided Integrity, Accuracy, and Compliance values (0-1). Returns weighted composite and pass/fail against configured thresholds. Score

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

AI workforce governance control plane. 29 governed MCP tools for decision classification (MAI framework), compliance scoring, audit chain verification, risk assessment, and multi-vendor AI governance. Built for enterprise AI compliance including NIST 800-53, CMMC 2.0, EU AI Act, and SOC 2. Every AI action is classified, audited, and governed through one contract.

Список инструментов сервера (29)

Технические названия из tools/list. Нужны только разработчикам.

classify_decision	Classify an AI agent decision using the MAI Framework (Mandatory/Advisory/Informational). Returns classification level, confidence score, gate requirements, and rationale.
evaluate_threshold	Compute the Storey Threshold — escalation rate (gates required / total operations). Returns current rate, status, and recommendations. Healthy band 10-18% is a design heuristic, not empirically validated.
score_governance	Compute weighted governance score from caller-provided Integrity, Accuracy, and Compliance values (0-1). Returns weighted composite and pass/fail against configured thresholds. Scores are caller-assessed — this tool applies weights and thresholds, not independent evaluation.
audit_pipeline	Query the audit ledger for governance entries. Search by operation name or retrieve recent entries. Returns hash-chained audit trail with MAI classification context.
monitor_agents	Monitor the status and health of all governed AI agents. Returns supervisor state, repair history, and failure counts.
map_compliance	Map GIA governance components to regulatory compliance frameworks (NIST AI RMF, EU AI Act, ISO 42001, NIST 800-53, LINDDUN, MITRE ATLAS). Shows which controls are implemented.
assess_risk_tier	Assess the risk tier of an AI system using rule-based mapping to EU AI Act categories (Unacceptable, High, Limited, Minimal). Returns tier and MAI governance recommendations. Classification is heuristic, not a legal determination.
generate_report	Generate a governance status report. Includes system health, threshold status, compliance coverage, and operational metrics.
system_status	Get full GIA system status including engine health, uptime, governance metrics, and configuration.
approve_gate	Approve or reject a pending MANDATORY gate decision. Lists pending gates if no gate_id provided. This is the human-in-the-loop mechanism for MANDATORY classifications.
seal_memory_pack	Create and hash-seal a new Governed Memory Pack (GMP). The pack becomes an immutable, TTL-bound institutional knowledge artifact with trust level enforcement.
load_memory_pack	Load a Governed Memory Pack into agent context. Validates TTL, trust level, role access, context class, and hash integrity before loading.
transfer_memory_pack	Transfer a memory pack between agents via a governed knowledge corridor. Creates a derived pack with transfer provenance. ALWAYS requires MANDATORY gate — no silent transfers.
compose_memory_packs	Compose multiple memory packs into a unified execution context. Highest risk level wins, shortest TTL wins, roles intersect, trust level contaminates downward.
distill_memory_pack	Distill governance patterns from usage history into a draft heuristic pack. Returns EPHEMERAL draft that requires MANDATORY gate to approve for production use.
promote_memory_pack	Promote a memory pack to a higher trust level after human review. This is how distilled EPHEMERAL packs become CASE or ORG packs. Requires MANDATORY gate.
record_value_metric	Record a workflow value metric — tracks time saved, risk blocked, success rate, autonomy level, and task complexity for ROI reporting.
record_governance_event	Record a governance event — tracks gates triggered, drift prevented, violations blocked, red team findings, and human interventions for impact reporting.
generate_impact_report	Generate a full economic + governance impact report. Returns pilot ROI data: time saved, cost avoided, risks blocked, success rate, autonomy trend, and confidence levels.
srt_run_watchdog	Run real health check probes from the MCP container (API health, frontend, disk, memory, TLS cert, DB, DNS). Returns actual measured values — never uses AI-provided data. Classification: INFORMATIONAL — read-only, no side effects.
srt_diagnose	Run the SRT Diagnostician on an incident. Matches finding to known playbooks, identifies root cause, and proposes a staged repair plan. Classification: ADVISORY — read-only analysis, no mutations.
srt_approve_repair	Approve or reject a pending SRT repair plan. Classification: MANDATORY — this is the human-in-the-loop gate. Repair plans CANNOT execute without explicit human approval. Pass action="approve" to approve or action="reject" to reject.
srt_generate_postmortem	Generate a structured postmortem report for a completed SRT incident. Includes timeline, root cause, what worked/failed, prevention actions, metrics (TTD/TTDiag/TTR), and optional playbook delta. Classification: ADVISORY.
verify_ledger	Verify the integrity of the hash-chained forensic audit ledger. Recomputes every SHA-256 hash from genesis and reports whether the chain is intact. Classification: INFORMATIONAL — read-only, no side effects.
gia_scan_environment	Run scout swarm to detect target environment — OS, containers, services, network, storage. Returns EnvironmentProfile for compatibility checking. Classification: INFORMATIONAL — read-only, no mutations. Scout outputs are redacted for sensitive content.
gia_list_packs	List available governed operations packs. Filter by intent (remediation/patrol/hardening/audit), category, risk level, or trust level. Classification: INFORMATIONAL.
gia_dry_run_pack	Preview remediation pack execution — shows hydrated commands, compatibility check, validation, blast radius. Returns inputsHash for approval binding (what-you-approved-is-what-ran). Classification: ADVISORY — read-only preview, no execution.
gia_apply_pack	Execute a remediation or hardening pack with MANDATORY gate approval. Requires inputsHash from gia_dry_run_pack (what-you-approved-is-what-ran binding). REJECTS patrol/audit packs (use gia_run_patrol for those). Hardening packs run preflight checks before execution. Classification: MANDATORY — human approval required.
gia_run_patrol	Execute a patrol or audit pack — read-only posture checks that produce findings or compliance evidence. Classification: ADVISORY for low/moderate sensitivity, MANDATORY for high sensitivity. REJECTS remediation/hardening packs (use gia_apply_pack for those). Audit packs produce deterministic pass/fail per NIST control — no AI interpretation.