Mark the current moment as a semantic checkpoint in the live-sync log. Use this when you've finished a coherent piece of work (feature complete, tests passing, a good place to stop) so reviewers can use the label as a compaction boundary. Optionally attach a structured trust assertion (e.g. tests...
Part of the Kai server.
Free to start. No card required.
AI agents invoke kai_checkpoint_now to trigger processes or run actions in Kai. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
kai_checkpoint_now can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"kai_checkpoint_now": {
"limits": [
{
"counter": "kai_checkpoint_now_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Kai policy for all 18 tools.
These attack patterns abuse exactly the kind of access kai_checkpoint_now gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Mark the current moment as a semantic checkpoint in the live-sync log. Use this when you've finished a coherent piece of work (feature complete, tests passing, a good place to stop) so reviewers can use the label as a compaction boundary. Optionally attach a structured trust assertion (e.g. tests-pass) for the review trust badge. Does NOT run kai capture.. It is categorised as a Execute tool in the Kai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kai MCP server in PolicyLayer and add a rule for kai_checkpoint_now: 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 Kai. Nothing to install.
kai_checkpoint_now is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kai_checkpoint_now 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 kai_checkpoint_now. 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.
kai_checkpoint_now is provided by the Kai MCP server (kai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Kai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.