Pretorin Compliance

Get a single risk with eager-loaded artifact_links.

Read metadata for the current Risk Assessment Report (RAR) in the active system/framework scope. This is proof-only: it never creates or regenerates a report, and returns not found when no current RAR exists.

Read the system's aggregate risk-assessment posture: inherent and residual distributions, weighted residual score, overdue reviews, and top risks.

Get system scope/policy information including excluded controls and Q&A

Use this BEFORE answering a specific scope question. Returns guidance, tips, example responses, and the current answer for ONE question. Pull only when ready to answer.

Poll for scope generation or review results. Returns structured findings with severity, affected question IDs, and recommended fixes. Status will be 'queued', 'running', 'succeeded', or 'failed'. Poll every 2 seconds until done.

Get the resolved source manifest for a system and evaluate it against currently detected sources. Shows which external sources (git, cloud, HRIS, etc.) are required, recommended, or optional, and whether each is currently satisfied. If no local manifest is configured, falls through to the platform's in-scope recommended source kinds.

List controls with stale inheritance — the source narrative changed but the inherited control hasn't been updated.

Get single STIG benchmark detail by ID including title, version, and release info.

Get which STIGs apply to a system based on its profile.

Get full detail for a single STIG rule including CCIs, check text, and fix text.

Get detailed information about a specific system including frameworks and security impact level

List issues across a whole system/framework rather than one control. Use this to find remediation work without walking every control. Each row carries control_implementation_id and issue_id for the treatment tools, plus lifecycle_status, gate_status, and is_blocking.

Get a system's applicable STIG test manifest. Full mode preserves scanner-ready check/fix definitions; use stig_id + rule_id for one exact definition, or mode=summary with limit/offset for a bounded discovery page. Responses include explicit pagination and truncation metadata.

Get detailed information about a specific vendor.

Get a vendor assessment with its frozen template snapshot and captured answers.

Get a vendor assessment template with its sections and question specs.

Get the organization-wide third-party-risk (TPRM) reporting dashboard: posture counts, by_tier / by_provider_type breakdowns, the 5x5 residual likelihood x impact heatmap (each cell carries a vendor count), and bounded document/contract expiry lists. horizon_days (1-365, default 90) sets the look-ahead window. Organization-wide: requires an org-scoped token with the vendor.pii or admin scope — system-scoped tokens are rejected. Note: per-cell heatmap vendor rosters are omitted here to stay within the response-size budget (heatmap_vendors_omitted is set to true); call list_vendors with a risk_tier filter to enumerate vendors in a tier.

Get audit and evidence history for a vendor.

Return one workflow's manifest, markdown instructions, and referenced tool schemas. Use mode=compact to preserve the complete playbook and validation contracts without schema annotations, section=<heading id> for one complete bounded section, or include_tool_schemas=false for a minimal {id, body} response when the harness already registered the tools.

Use this FIRST when starting a compliance workflow. Returns the lifecycle state for a system+framework: which stage needs work (scope, policies, controls, evidence), what the next action is, and progress counts. `stages.controls.controls_with_unmet_baseline_expectations` counts in-scope controls with an unmet baseline-tier evidence expectation. Lightweight — no content, just status.

Import a .ckl/.cklb file into a checklist's per-rule reviews (review axis). Full-fidelity complement to submit_test_results: ingests asset metadata + the four DISA statuses + finding details/comments + severity override, reconciled against the benchmark. Returns match/import counters + reconciles flag + capped rule-id buckets (the full per-rule outcomes are omitted for size; use the CLI for full detail). A non-reconciling import (rules dropped) returns an error result — never treat it as complete. Writes are refused outside the active context system.

Import an XCCDF scan document (SCAP/OpenSCAP results) into the system test axis. Separate from import_stig_checklist (the .ckl/.cklb review axis). The test axis is system-scoped, so the response reports how many checklists on the system the scan affects. Use this to push a scanner recipe's XCCDF results so they derive DISA statuses across all checklists bound to the same benchmark.

Import a SIG-Lite or CAIQ-Lite xlsx workbook as a vendor assessment template. By default dry_run is true and returns a preview; set dry_run false plus acknowledge_license_rights true to persist.

AI-infer applicable STIGs from a system's profile.

Read only the exact evidence artifact frozen into this evidence-ID review child. Control evidence-set children use assignment-scoped search_evidence instead.

Read only the exact canonical Issue frozen into this issue-triage child. The server derives Issue and control-implementation identity from the trusted assignment.

Inspect the bounded content-free typed-write receipt ledger and matching child-Plan artifacts for this assigned Campaign item. Use before retrying an intended write after an uncertain response.

Launch a vendor assessment from a template, freezing the template snapshot.

Link an existing evidence item to a control within exactly one active system/framework scope. Bind it to exactly one declared evidence expectation so the control's coverage map marks that expectation covered, or explicitly record why the artifact is intentionally unbound. Narrative citations ground claims but never satisfy expectation coverage.

Link an existing evidence item to a per-system CCI implementation row. Use this when you already have the CCI implementation UUID (e.g., from get_cci_implementation or get_cci_status). This governed stig_scan write must match the active MCP system/framework context; agents cannot override that boundary.

Link an existing evidence item to a per-system assessment objective implementation row (CMMC / NIST 800-171A). Use this when you have the objective implementation UUID (e.g. from list_objectives or get_objective_implementation). The platform also mirrors the evidence into the parent control's library. This governed write must match the active MCP system/framework context; agents cannot override that boundary.

Link an existing evidence item to a STIG rule workflow. Lazy-creates the workflow row if none exists yet for (system, stig_rule). Use this to attach remediation proof, mitigating-control documentation, or waiver-justification artifacts to a failing rule. This governed stig_scan write must match the active MCP system/framework context; agents cannot override that boundary.

Link existing evidence to a vendor. Set vendor_id to null to unlink.

Attach an artifact (control, evidence, finding, monitoring_event, or vendor) to a risk. Pass exactly one of control_id / evidence_id / finding_id / monitoring_event_id / vendor_id. Pass framework_id when linking a control.

Link an uploaded evidence item as the current snapshot for a system_spec kind, so it surfaces on the scope page. Use AFTER upload_evidence returns an evidence id. `kind` is one of the snapshot kinds (boundary_diagram, network_dfd, ppsm, interconnection) — call list_artifact_requirements for the authoritative set for this system. The asset inventory is NOT a snapshot kind; attest it with attest_spec_inventory instead. Requires an active workflow (call start_task first).

List the 5 auditor-required system_spec artifact kinds for a system (asset inventory + 4 snapshot kinds). Returns each kind's effective_required, optional/toggled-off state, attestation timestamp, and rationale.

List formal assessments for one system, including status and immutable snapshot lifecycle fields used by the Auditor Portal.

List bounded local Plan-backed Campaign summaries for one trusted project root, ordered by immutable (created_at, Campaign Plan ID) and keyset-paginated. This local observation tool remains available during platform authentication or consent outages.

List CCI items with optional filters by NIST control ID or status.

List all control families for a specific framework with AI context (domain summary, risk context, implementation priority)

List controls for a framework, optionally filtered by control family

List all available compliance frameworks (NIST 800-53, FedRAMP, SOC 2, ISO 27001, etc.)

List per-system assessment objective implementation rows (CMMC / NIST 800-171A). Filter by framework_id + control_id for one control's objectives, or by status. Each row carries effective status, status_source, narrative, evidence_ids, and has_status_conflict. control_id is normalized server-side (CMMC/800-171 IDs keep their native shape). Objectives are the assessable leaf a C3PAO adjudicates.

List organization policies available for questionnaire work

List validated OSCAL export artifacts (SSP/SAR/SAP/POA&M/component-definition) for a system. Server-filtered to succeeded generation AND valid validation.

List recent plans (newest first), with optional filtering by state, workflow, and scope. Returns compact summaries — call get_plan for the full record once a plan is selected. Use this at session start to find an existing plan to resume instead of creating a duplicate.

List loaded recipes with their summary metadata (id, name, tier, description, use_when, produces). Filter by tier, produces, and connected system sources. Use this to discover which recipes are available, then call get_recipe(id) to read the full body.

List signed risk-attestation envelopes newest first for audit verification.

List org-level risk library templates available to the org. Optional category filter.