This record as markdown: /tools/hybridlabor-api-aos/manage-checkpoint.md
What manage_checkpoint does on Aos
AI agents call manage_checkpoint to permanently remove resources in Aos, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why manage_checkpoint is rated Critical
The tool spans multiple categories: listing/reading snapshots (Read), storing snapshots (Write), restoring a snapshot which irreversibly overwrites the current sub-network state (Destructive), and deleting snapshots (Destructive). Per the rules, the most severe applicable category wins. Restoring a full snapshot of a sub-network can overwrite live work without recovery, and deleting snapshots is irreversible.
From the tool's definition 'restore' and 'delete a full snapshot' — restoring overwrites current state irreversibly; deleting a snapshot permanently removes it
Attacks that exploit this kind of access
The rule that runs manage_checkpoint safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_checkpoint, this is the rule to start with:
manage_checkpoint is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Aos, apply this rule, and every manage_checkpoint call is checked against it from then on.
Questions about manage_checkpoint
Store / restore / list / delete a full snapshot of a sub-network — an. It is categorised as a Destructive tool in the Aos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Aos MCP server in PolicyLayer and add a rule for manage_checkpoint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Aos. Nothing to install.
manage_checkpoint is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_checkpoint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for manage_checkpoint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
manage_checkpoint is provided by the Aos MCP server (@hybridlabor-api/aos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aos, and thousands of servers like it.
Across the catalogue