5 tools. 2 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Free to start. No card required.
Full per-tool breakdown → Model it in the token calculator →
Destructive tools (clear_namespace, delete_memory) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
{
"clear_namespace": {
"deny_if": [
{
"conditions": [],
"on_deny": "Blocked by default. Requires approval."
}
]
}
} Destructive tools should never be available to autonomous agents without human approval.
{
"get_memory": {
"limits": [
{
"counter": "get_memory_per_minute",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
} Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Agent Memory server exposes 2 destructive tools including clear_namespace, delete_memory. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.
5 tools across 2 categories: Destructive, Read. 3 are read-only. 2 can modify, create, or delete data.
Register the Agent Memory MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.
Starter policies for each. Same risk classification, live on your fleet in minutes.
Deterministic rules across all 5 Agent Memory 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.