AI Client Access (MCP)

QuantAssure exposes your compliance data to AI tools via the Model Context Protocol — so Claude, Cursor, or any MCP-capable client can query findings, risks, controls, and posture, and (with your approval) make changes, all under your organisation's permissions.

Connecting a Client

1. An administrator registers the client for your organisation (client registration is restricted to owners and admins — there is no open self-registration).
2. Point your AI tool at the QuantAssure MCP endpoint. The client walks through OAuth: you sign in as yourself and see a consent screen listing exactly what the client is requesting before you approve.
3. The client receives scoped tokens. Every action it takes is attributed to you in the audit log — "the agent did it" is never an anonymous entry.

What Clients Can Do

The tool surface covers the whole compliance conversation, not just lookups. A session with your assistant can move from "where do we stand?" to a generated audit pack without leaving the chat:

1. Find the gaps — read tools list and inspect findings (AI-adjusted severities included), risks, action items, framework controls with your org's statuses, and posture summaries.
2. Close them with evidence — create_control_evidence attaches evidence to a control (by code, e.g. ISM-1504), and update_control_status records the applicability and compliance determination with a required rationale, captured in the audit trail.
3. Author the policies behind the controls — create_policy drafts a new policy from markdown, and update_policy publishes a revised version with a change summary. Revisions go through the same version history as the in-app editor: the previous content is archived as a snapshot, never overwritten. list_policies and get_policy read the register, current content, and version history.
4. Run a fresh scan — trigger_run dispatches an Assure Agent collection run for a scope, through exactly the same path as the dashboard's run button.
5. Read the results — get_run_status follows the run through collection and AI triage; once it completes, the read tools pick up the freshly triaged findings.
6. Produce the audit pack — generate_report creates any report type (AI Decision Audit Trail, SLA Compliance, and the rest), and get_report reads back the summary plus a dashboard link to the full report.

Write tools also cover the day-to-day in between: create and update risks and actions, update finding statuses, and keep the asset register current — list_assets reads the inventory, and upsert_asset records an asset by its stable source identity, so repeating the same upsert updates the existing record instead of duplicating it (the same semantics the collection pipeline uses). Every write is audit-logged with your identity.

Each tool group carries its own OAuth scope — for example findings:read, evidence:write, runs:write/runs:read, and reports:write/reports:read. The consent screen lists exactly the scopes a client requests, and a client granted read-only access stays read-only.

Security Posture of the Endpoint

The MCP surface is hardened as a first-class product API: per-token rate limiting, strict session lifecycle with idle expiry, CSRF-protected consent, request size caps, and org-scoped authorisation on every tool. Your data is only reachable with tokens minted through the consent flow you approved.