Documentation Index
Fetch the complete documentation index at: https://docs.complyhat.ai/llms.txt
Use this file to discover all available pages before exploring further.
Fourteen entity tools plus guidance. Each tool dispatches by mode. All callable via https://complyhat.ai/api/mcp. Audit-tagged citations ([EXTRACTED], [INFERRED], [AMBIGUOUS]) appear in every prose field.
adversarial
Adversarial robustness findings.
| Mode | Description |
|---|
list_by_model | List adversarial findings for a model. |
get | Get one finding by ID. |
submit | Submit a new finding (host-driven; ComplyHat does not generate attacks). |
alerts
Compliance alerts and the rules that trigger them.
| Mode | Description |
|---|
list / get | List alerts or get one by ID. |
update | Acknowledge or resolve an alert. |
rules_list / rules_create | List or create alert rules. |
audit_events
Append-only audit trail for compliance-relevant actions.
| Mode | Description |
|---|
list / get | List events with filters or get one by ID. |
emit | Emit a new audit event from the host agent. |
bias_tests
Bias and fairness tests against registered models.
| Mode | Description |
|---|
list / get | List tests for a model or get one result. |
run | Run a bias test against a model and dataset. |
list_schedules / create_schedule | List or create recurring schedules. |
data_governance
Data sources, consent records, and lineage.
| Mode | Description |
|---|
sources_list / sources_create | List or register data sources. |
consent_list / consent_create | List or record consent grants. |
lineage_list / lineage_create | List or create lineage entries. |
drift
Drift monitors, status, alerts, and snapshot ingestion.
| Mode | Description |
|---|
monitors_list / monitors_create | List or create drift monitors. |
monitors_status | Current status of a monitor. |
alerts_list_by_model | Drift alerts for a model. |
snapshots_list / snapshots_submit | List snapshots or submit a new one from the host. |
explainability
Coalition-attribution and LIME runs against registered models.
| Mode | Description |
|---|
list_by_model / get | List runs for a model or get one’s results. |
run | Trigger a new run. |
frameworks
Regulatory framework status, gaps, and applicability.
| Mode | Description |
|---|
status | Overall coverage status for the organization. |
gaps | Gaps between current state and framework requirements. |
check | Check whether a framework applies to a model or use case. |
model_cards
Model cards rendered as structured, audit-tagged documents.
| Mode | Description |
|---|
list / get | List or retrieve model cards. |
create / update | Create from a model registration, or update. |
models
The model registry — the root entity most other tools reference.
| Mode | Description |
|---|
list / get | List or retrieve registered models. |
register / update | Register a new model or update metadata. |
obligations
Per-framework regulatory obligations and how they map to your models.
| Mode | Description |
|---|
list / get | List obligations or get one by ID. |
list_by_model | Obligations applicable to a specific model. |
assess | Assess whether a model satisfies a given obligation. |
reg_intel
Regulatory intelligence: changes, deadlines, relevance.
| Mode | Description |
|---|
changes | Recent regulatory changes. |
deadlines | Upcoming compliance deadlines. |
relevance | Relevance scoring of changes against your models. |
change_detail | Full detail for one regulatory change. |
reports
Compliance reports and PDF downloads.
| Mode | Description |
|---|
list / get | List or retrieve reports. |
get_pdf_url | Signed URL for the report PDF. |
generate | Generate a new report for a model and framework. |
{
"tool": "reports",
"arguments": { "mode": "generate", "model_id": "mdl_...", "framework": "eu-ai-act" }
}
wiki
Per-tenant Karpathy-style compliance wiki backing every report and citation.
| Mode | Description |
|---|
list / read | List pages or read one. |
write | Write or update a page. Accepts host-supplied embeddings (ComplyHat does not generate them). |
search | Lexical or semantic search across pages. |
link | Create a link between pages. |
draft_from_finding | Draft a page from a compliance finding. |
log_list | List immutable audit log entries. |
lint / archive | Lint a page or archive it. |
guidance
The fifteenth tool. Returns the canonical SKILL.md body for any skill or agent.
| Argument | Type | Description |
|---|
kind | "skills" or "agents" | Resource namespace. |
slug | string | Skill or agent slug from the lists below. |
{
"tool": "guidance",
"arguments": { "kind": "skills", "slug": "bias-test-prep" }
}
complyhat://{kind}/{slug} for hosts that auto-include resources.
Skills
| Slug | Purpose |
|---|
bias-test-prep | Dataset preparation for bias testing. |
compliance-checklist | Per-framework checklists. |
model-documentation | Model card authoring. |
regulatory-mapper | Map use cases to frameworks. |
risk-classification | EU AI Act risk-tier classification. |
Agents
| Slug | Purpose |
|---|
adversarial-tester | Coordinates host-driven adversarial submissions. |
bias-tester | Runs scheduled bias tests, revalidates on regulatory change. |
data-governance-auditor | Audits sources, consent, lineage. |
drift-detector | Watches drift signals, raises alerts. |
explainability-tester | Schedules explainability runs. |
model-card-writer | Drafts and updates model cards. |
report-generator | Generates framework reports. |
revalidation-orchestrator | Triggers downstream revalidation when regulations change. |
