Policy Engine
为每条命令、每台设备与每个环境应用灵活的执行规则与策略。
- 基于角色的策略
- 灵活的规则构建器
- 访问与权限控制
Anvil 是 Membara 面向受控 AI 与机器操作的安全产品品牌。Membara Commander 仍是独立服务边界中的核心工具,负责 identity、policy、approval、execution、device sessions、audit 与 evidence。
Commander
128
Policies
3
Pending approval
8
Device sessions
248
Evidence records
Inspect staging health
Identity-bound action
Apply controlled change
Identity-bound action
Production mutation request
Identity-bound action
Execute safely.
With control and evidence.
Commander trust boundary stays separate from the public website
Anvil principle
“AI should never gain more authority than the identity, policy, approval, and environment allow.”
Anvil 承载安全产品品牌身份;Identity、enrollment、OIDC、MCP、device grants、execution、audit、evidence、privacy 与 service terms 仍由 Commander Core 管理。
Core capabilities
Commander 将 identity、authority、policy、approval、execution 与 evidence 绑定在一个可审计的 control plane 中。
为每条命令、每台设备与每个环境应用灵活的执行规则与策略。
在执行前管理审批流程,并支持可配置的工作流。
完整记录每项活动,并以防篡改方式支持合规与调查。
安全管理服务器、IoT 设备与本地系统连接。
可靠执行命令与自动化任务,并保持可监控。
收集执行证据,包括输出、文件、截图与系统日志。
Commander 确定 principal 身份、拥有的 authority、允许触达的 environment、是否需要 approval,并记录执行结果与 evidence。
Commander
128
Policies
3
Pending approval
8
Device sessions
248
Evidence records
Inspect staging health
Identity-bound action
Apply controlled change
Identity-bound action
Production mutation request
Identity-bound action
Execution authority is explicit, scoped, and tied to authenticated identity and target context.
When identity, policy, approval, target binding, or evidence requirements are not satisfied, execution does not silently continue.
Commander keeps its own app, database, OIDC, MCP, operational data, privacy policy, and terms separate from the corporate website.
Membara Anvil Commander
Use Anvil to understand the product. Use Commander to authenticate, enroll, connect devices, call MCP tools, approve actions, execute work, and inspect evidence.