Save detailed explanations provided by Claude
AI agents use save_explanation to create or update resources in SAM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAM environment.
This tool stores explanations (creates new records or updates existing ones) without destructive intent. It is Write rather than Read because it persists data, and not Destructive because saving is reversible—the data can be modified or removed later.
From the tool's definition Tool name and description indicate it creates or modifies data: 'Save detailed explanations' shows persistent storage of information without deletion.
Documented attack patterns abuse exactly the kind of access save_explanation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAM, and nothing reaches the server without passing your rules. This is the rule we recommend for save_explanation:
{
"version": "1",
"default": "deny",
"tools": {
"save_explanation": {
"limits": [
{
"counter": "save_explanation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_explanation 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 detailed explanations provided by Claude. It is categorised as a Write tool in the SAM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAM MCP server in PolicyLayer and add a rule for save_explanation: 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 SAM. Nothing to install.
save_explanation 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 save_explanation 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 save_explanation. 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.
save_explanation is provided by the SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAM, 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.
37 SAM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.