memory_get_preferences
AI agents call memory_get_preferences to retrieve information from Eve Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves preference information from a shared memory service. There are no side effects, modification, deletion, or external execution implied by the name. The operation is read-only and returns data to the caller. Low severity due to no capability to modify state or trigger external actions.
From the tool's definition Tool name 'memory_get_preferences' indicates retrieval of preference data. The description is empty, but the name and context within a memory service suggest this retrieves stored preferences without modification.
Attacks that exploit this kind of access
memory_get_preferences. It is categorised as a Read tool in the Eve Memory MCP Server, which means it retrieves data without modifying state.
Register the Eve Memory MCP server in PolicyLayer and add a rule for memory_get_preferences: 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 Eve Memory. Nothing to install.
memory_get_preferences 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 memory_get_preferences 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_get_preferences. 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_get_preferences is provided by the Eve Memory MCP server (sherifkozman/eve-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →