Search through conversation history and long-term memories. WHEN TO USE: - When user asks about past discussions, decisions, or preferences - When user references something
AI agents call memory_search to retrieve information from Universal Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though memory_search only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Search through conversation history and long-term memories. WHEN TO USE: - When user asks about past discussions, decisions, or preferences - When user references something. It is categorised as a Read tool in the Universal Memory MCP Server, which means it retrieves data without modifying state.
Register the Universal Memory MCP server in PolicyLayer and add a rule for memory_search: 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 Universal Memory. Nothing to install.
memory_search 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_search 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_search. 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_search is provided by the Universal Memory MCP server (slicenferqin/universal-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.