ISMS Copilot Docs

Tokens, scopes, and security

How pat-isms tokens work: scopes, revoke, expiry, and hard limits.

Account tokens let an MCP client act as your user, limited by the scopes you selected when the token was created.

Prefix and lifecycle

StepBehaviour
CreateSettings → Connected apps → Create token
DisplayFull secret shown once; starts with pat-isms-
StoreClient config only; never commit to git
RevokeSame Settings page; takes effect immediately
ExpiryOptional at creation

Scopes (typical)

Exact labels in the UI may vary slightly; the intent is:

CapabilityReadWrite / act
Account infoyesno
Workspaceslistno
Documentslist metadata only (no get-by-ID tool)no
Memoriesyescreate / edit when granted
Conversationsn/astart and send when granted

Grant the minimum set for the agent’s job. A read-only workspace token cannot start conversations.

Hard limits (by design)

  • Beyond mode is not available over MCP. Use the web app.
  • Advanced Data Protection cannot be toggled via the token. The agent can report status; you change it in Settings → Data Protection.
  • Rate limits apply (on the order of ~120 requests/minute per token; concurrent conversations are capped per account). If you hit limits, back off and retry.
  • Tokens do not unlock the model API (sk-isms-…) or Embed partner billing.

Security checklist

  1. Name tokens by device or purpose (claude-laptop, cursor-ci).
  2. Prefer short expiry for temporary machines.
  3. Revoke when a laptop is lost or a CI secret rotates.
  4. Never put pat-isms-… in public repos, screenshots, or support tickets.

Usage counts against your normal chat subscription and plan limits, not against API prepaid credits.

On this page