PricingAPI keys
  • Overview
  • Quickstart
  • Authentication
  • Overview
  • Format API
  • Create a run
  • Runs and results
  • Bulk runs
  • Editing a Format package
  • Structured output
  • Format catalog
  • Errors and spend
  • Cookbook
  • Embed a Format in your product
  • Waiting for runs and jobs
  • Agents
  • Agent Completions
  • Scheduled
  • Create a schedule
  • Advanced: run a schedule via API
  • Runs and results
  • Run webhooks
  • Safe automation
  • Best practices

Enterprise

Safe automation

Guidelines for using Sume APIs and tools from agents without leaking secrets or crossing workspace boundaries.

Use the public API, CLI, and MCP in a way that keeps each workspace isolated and keeps billing clear. Related: MCP tools and gates, CLI security.

Workspace isolation

The API key or the app session selects the workspace. Tools must not accept a workspace id from the user. The only exception is a product that explicitly supports a change between workspaces.

Credit-spending actions

Generation and analysis creation can spend credits. Agent tools must make those actions explicit. Agent tools must also keep read-only operations separate.

On hosted MCP, the best choice for read-only exploration is OAuth mcp:read. Before you use paid tools such as generate_image / avatars_create, grant mcp:write (or use an API key). Write calls and paid calls must send idempotency_key. The legacy allow_write / allow_paid arguments are optional.

Logging

Safe logs include:

  • request ids,
  • job ids when necessary,
  • high-level status,
  • sanitized media metadata.

Unsafe logs include:

  • API keys,
  • signed URLs,
  • raw private media URLs,
  • too much user content or too many transcripts.

On this page

  • Workspace isolation
  • Credit-spending actions
  • Logging