Save important information to memory with ML auto-detection
AI agents use save_memory 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 creates or modifies data in a memory system reversibly. While it doesn't delete data (which would be Destructive), it does persistently store information that could affect AI behavior across platforms. The 'auto-detection' aspect introduces medium risk: the AI agent may save unintended or sensitive information without explicit user approval, affecting future interactions.
From the tool's definition Tool name 'save_memory' and description 'Save important information to memory' indicate data creation/modification. The phrase 'with ML auto-detection' suggests automated writing based on inferred context.
Documented attack patterns abuse exactly the kind of access save_memory 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_memory:
{
"version": "1",
"default": "deny",
"tools": {
"save_memory": {
"limits": [
{
"counter": "save_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_memory 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 important information to memory with ML auto-detection. 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_memory: 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_memory 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_memory 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_memory. 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_memory 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.