AI agents use create_checkpoint to create or update resources in Novyx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Novyx environment.
Creating a checkpoint modifies state (adds a new rollback point in the mission history) but is reversible—the checkpoint itself can be discarded or the system can revert to previous states. This is a data modification action without destructive finality. It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool creates a checkpoint which is a reversible operation that establishes a rollback point. The description states 'Create a checkpoint for a mission (rollback point)' — checkpoints are savepoints that can be reverted without permanent data loss.
Documented attack patterns abuse exactly the kind of access create_checkpoint gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Novyx, and nothing reaches the server without passing your rules. This is the rule we recommend for create_checkpoint:
{
"version": "1",
"default": "deny",
"tools": {
"create_checkpoint": {
"limits": [
{
"counter": "create_checkpoint_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_checkpoint stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a checkpoint for a mission (rollback point). It is categorised as a Write tool in the Novyx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Novyx MCP server in PolicyLayer and add a rule for create_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 Novyx. Nothing to install.
create_checkpoint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_checkpoint is provided by the Novyx MCP server (novyxlabs/novyx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 120 Novyx tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
120 Novyx tools catalogued and risk-classified — across an index of 42,500+ MCP servers.