MCP Tool Catalog

The AutoCISO MCP server exposes 23 tools: 22 read-only tools and one write tool, risk_create_draft. This page explains how to read the catalog and groups tools by area; the table at the bottom is generated from the same manifest the SDKs are built from, so it never drifts.

How to read the catalog

• Scope — mcp:read for every read tool; mcp:write for risk_create_draft.
• Arguments — taken from each tool’s published input schema. Most read tools take no arguments.
• PII masking applies to all results. Emails are masked to a***@domain.com and personal names are redacted. A type that promises a real email is a lie — never rely on full identity fields in a result.
• Result caps. Some tools silently return a partial result set with no continuation token. The catalog flags each one. The only tool with real pagination is audit_trail_search.

Access (9 tools)

access_stale_accounts, access_concentration, access_privileged_delta, access_high_risk_lifecycle, access_anomaly_discovery, access_offboarding_violations, access_normalization_health, access_department_risk, access_security_debt_trend.

These power the access-intelligence surface. Results carry masked identity fields. access_security_debt_trend accepts an optional months argument (default 6).

const stale = await client.access.staleAccounts();
const debt  = await client.access.securityDebtTrend({ months: 12 });

stale = client.access.stale_accounts()
debt  = client.access.security_debt_trend(months=12)

Reviews (2 tools)

uar_status, access_reviews_list — user access review status and campaign completion.

ISO 27001 (3 tools)

iso_gap_status, iso_soa_summary, iso_controls_list. Each accepts an optional projectId; if omitted, the first active ISO project is used.

const gaps = await client.iso.gapStatus();
const soa  = await client.iso.soaSummary({ projectId: 'iso_…' });

gaps = client.iso.gap_status()
soa  = client.iso.soa_summary(project_id="iso_…")

Risk (3 tools)

risk_register_list, risk_get, and the write tool risk_create_draft.

const risks = await client.risk.registerList();   // finalized only
const one   = await client.risk.get({ id: 'risk_…' });

risks = client.risk.register_list()   # finalized only
one   = client.risk.get(id="risk_…")

// Requires mcp:write + MCP write enabled for your org.
const draft = await client.risk.createDraft({ title: 'Vendor X data residency' });
// On a read-only org this throws AutocisoPermissionError (NOT_PERMITTED).

# Requires mcp:write + MCP write enabled for your org.
draft = client.risk.create_draft(title="Vendor X data residency")
# On a read-only org this raises AutocisoPermissionError (NOT_PERMITTED).

Suppliers (2 tools)

supplier_list, supplier_assessment_status — third-party inventory and assessment completion.

Evidence & Audit (2 tools)

evidence_log (capped at 50 entries), audit_trail_search.

audit_trail_search is the only paginated tool. It returns a wrapped object — { items, total, limit, offset } — not a bare array. Use limit/offset to page and total for the full count.

const page = await client.audit.trailSearch({ limit: 25, offset: 0 });
console.log(page.items.length, 'of', page.total);

page = client.audit.trail_search(limit=25, offset=0)
print(len(page.items), "of", page.total)

{
  "items": [
    { "id": "aud_…", "action": "risk.updated", "actor": "a***@domain.com", "at": "2026-06-20T08:00:00Z" }
  ],
  "total": 184,
  "limit": 25,
  "offset": 0
}

Maturity & Posture (2 tools)

maturity_scores (capped result set), posture_summary (a single roll-up — the recommended first call).

Generated tool reference

The table below is generated from the committed MCP manifest at build time — the same artifact the SDKs are generated from. It always reflects the live tool surface.

23 tools (22 read-only, 1 write). Generated from the committed MCP manifest (the same artifact the SDK is built from).

All results are PII-masked: emails become a***@domain.com and personal names are redacted. The Masked column flags tools whose results commonly carry identity fields. The Result notes column flags pagination and silent result caps.