AI agents call search_memory to retrieve information from Mem0 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches through stored memories and returns matching results. It is a read-only operation that queries data without creating, modifying, deleting, or destroying anything. The search functionality is a classic Read operation with minimal risk if misused by an AI agent—worst case would be exposure of sensitive information already stored in the memory system, but no data modification or destruction occurs.
From the tool's definition Tool name 'search_memory' and description '搜索记忆' (search memory in Chinese) indicate a query/retrieval operation without side effects.
Attacks that exploit this kind of access
搜索记忆. It is categorised as a Read tool in the Mem0 MCP Server, which means it retrieves data without modifying state.
Register the Mem0 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 Mem0. 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 Mem0 MCP server (mem0-mcp-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 →