Search through stored memories using full-text search
AI agents call search_memory to retrieve information from Claude Memory Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search over persistent memory storage, which is fundamentally a read operation. It queries and retrieves data but does not create, modify, delete, or execute external operations. The search capability poses minimal security risk—the worst outcome is exposure of sensitive information already stored in the memory system, but the tool itself cannot alter or destroy data.
From the tool's definition Tool name 'search_memory' and description 'Search through stored memories using full-text search' indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search through stored memories using full-text search. It is categorised as a Read tool in the Claude Memory Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory Server MCP server in PolicyLayer and add a rule for search_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 Claude Memory Server. Nothing to install.
search_memory 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 search_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 search_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.
search_memory is provided by the Claude Memory Server MCP server (xiy/claude-memory-server). 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 →