Save a checkpoint so future sessions know what was done and why. REQUIRED: call this as your final step after completing any user-requested task, before responding to the user. Also call when hitting a blocker or changing direction mid-task.
AI agents use create_checkpoint to create or update resources in Local Rag — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local Rag environment.
This tool writes metadata about task completion and reasoning to a checkpoint system, enabling stateful session memory. It modifies state reversibly without side effects beyond data storage. The blast radius is minimal: a corrupted checkpoint affects only future context within the same session, not external systems or data integrity.
From the tool's definition 'Save a checkpoint' — creates and stores a checkpoint record to preserve state and task history. Does not delete, execute commands, or move money. The action is reversible (checkpoints can be overwritten or cleared).
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 Local Rag, 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.
Save a checkpoint so future sessions know what was done and why. REQUIRED: call this as your final step after completing any user-requested task, before responding to the user. Also call when hitting a blocker or changing direction mid-task. It is categorised as a Write tool in the Local Rag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Local Rag 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 Local Rag. 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 Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.