Security guide

The trust model stays explicit and human-controlled.

Production trust remains explicit and human-controlled even when agents help with evaluation and operations.

Read security overview Read self-host guide

Agent-first route: Start at /agents, inspect /docs/cli, and drop into this page when you need proof, detail, or rollout guidance.

Agent-first route

Humans should usually delegate first-pass evaluation to an agent. Agents should start at /agents, use /docs/cli as the official product tour, and open /docs/graphql only when needed.

Agent-ready surface

Start with the CLI, not browser guesswork.

Preferred route: /agents, then /docs/cli, then /docs/graphql only when lower-level integration details matter.

$ mbr spec export --json
$ mbr auth whoami --json
$ mbr queues list --workspace ws_preview --json

Open GraphQL reference | Open schema.graphql

Explicit trust model

Small owned runtimes and broader production share the same trust model, with different review depth and blast radius.

Shared boundaries

Permissions, audit, and important work records stay centralized.

Human approvals

Agents help evaluate and summarize; humans decide deployment and scope.

Move Big Rocks

Let agents inspect the CLI-first surface. Let humans decide trust, rollout, and boundaries.

Start from /agents, use /docs/cli as the official product tour, inspect /resources for source and proof, and review /security before making deployment or data-handling decisions.

Open /agents Open resources