Call this BEFORE telling the user a task is done. Captures the full problem→solution context as a structured memory for future sessions. Use after: bug fixes, feature implementations, refactors, config changes, architecture decisions. Every completed task = one checkpoint.
Risk signalsBulk/mass operation — affects multiple targets
Part of the Nan Forget server.
Free to start. No card required.
AI agents invoke memory_checkpoint to trigger processes or run actions in Nan Forget. 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.
memory_checkpoint 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": {
"memory_checkpoint": {
"limits": [
{
"counter": "memory_checkpoint_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Nan Forget policy for all 13 tools.
These attack patterns abuse exactly the kind of access memory_checkpoint 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.
Call this BEFORE telling the user a task is done. Captures the full problem→solution context as a structured memory for future sessions. Use after: bug fixes, feature implementations, refactors, config changes, architecture decisions. Every completed task = one checkpoint.. It is categorised as a Execute tool in the Nan Forget MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nan Forget MCP server in PolicyLayer and add a rule for memory_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 Nan Forget. Nothing to install.
memory_checkpoint 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 memory_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 memory_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.
memory_checkpoint is provided by the Nan Forget MCP server (nan-forget). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Nan Forget 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.