Safe automation
Use the public API, CLI, and MCP in ways that preserve workspace isolation and billing clarity. Related: MCP tools and gates, CLI security.
Workspace isolation
API keys and app sessions determine the workspace. Tools should not accept user-supplied workspace ids unless the product explicitly supports switching workspaces.
Credit-spending actions
Generation and analysis creation can spend credits. Agent tools should make
those actions explicit and keep read-only operations separate. On hosted MCP,
prefer OAuth mcp:read for read-only exploration; grant mcp:write (or use
an API key) before paid tools such as generate_image / avatars_create.
idempotency_key is required on writes/paid; legacy allow_write /
allow_paid are optional.
Logging
Safe logs include:
- request ids,
- job ids when needed,
- high-level status,
- sanitized media metadata.
Unsafe logs include:
- API keys,
- signed URLs,
- raw private media URLs,
- excessive user content or transcripts.

