Search through stored memories using semantic search. Finds memories related to your query even if they don\
AI agents call search_memory to retrieve information from AgentCortex MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search over stored memories, returning matching results without creating, modifying, deleting, or executing anything. It is a pure read operation with minimal blast radius—even if an AI agent misuses it, the worst outcome is accessing memories from the current codebase context, which is the tool's intended purpose.
From the tool's definition Tool name 'search_memory' and description 'Search through stored memories using semantic search. Finds memories related to your query' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Search through stored memories using semantic search. Finds memories related to your query even if they don\. It is categorised as a Read tool in the AgentCortex MCP MCP Server, which means it retrieves data without modifying state.
Register the AgentCortex 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 AgentCortex MCP. 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 AgentCortex MCP server (sage-hq/agentcortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_memory is one line of AgentCortex's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →