Retrieve memories with optional filtering by type and date range. Returns memories in reverse chronological order (newest first).
AI agents call get_memories 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 queries and retrieves stored memory data with optional filters (type, date range) and returns results in a specific order. It has no side effects, does not modify data, execute code, or trigger external operations. It is a straightforward Read operation consistent with search/list/get/fetch category semantics.
From the tool's definition Tool description states 'Retrieve memories' with optional filtering parameters. The verb 'Retrieve' and the read-only nature of fetching stored memories without modification indicate a data retrieval operation.
Attacks that exploit this kind of access
Retrieve memories with optional filtering by type and date range. Returns memories in reverse chronological order (newest first). 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 get_memories: 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.
get_memories 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 get_memories 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 get_memories. 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.
get_memories 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.
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 →