AI agents call load_preset to retrieve information from myAI Memory Sync without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user preferences and configuration data. While the description is empty (lowering confidence slightly), the name and server purpose indicate it performs a retrieval operation with no side effects. Severity is medium because presets may contain personal details and code standards, making unauthorized access or misuse a concern, but the tool itself is non-destructive and non-financial.
From the tool's definition Tool name 'load_preset' suggests retrieval of stored configuration data. Sibling tools include 'list_presets', 'get_section', 'get_template' (all Read operations) and 'remember' (Write).
Documented attack patterns abuse exactly the kind of access load_preset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and myAI Memory Sync, and nothing reaches the server without passing your rules. This is the rule we recommend for load_preset:
{
"version": "1",
"default": "deny",
"tools": {
"load_preset": {}
}
}load_preset is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
load_preset. It is categorised as a Read tool in the myAI Memory Sync MCP Server, which means it retrieves data without modifying state.
Register the myAI Memory Sync MCP server in PolicyLayer and add a rule for load_preset: 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 myAI Memory Sync. Nothing to install.
load_preset is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_preset 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 load_preset. 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.
load_preset is provided by the myAI Memory Sync MCP server (jktfe/myaimemory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from myAI Memory Sync, 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.
10 myAI Memory Sync tools catalogued and risk-classified — across an index of 43,000+ MCP servers.