Export all your memories as encrypted blobs. For migration to
AI agents call memory.export to retrieve information from Sylex Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and packages stored memory data for the user. While the blast radius is medium (exporting all memories could expose sensitive information if intercepted or misused), the action itself is read-only—it does not modify, delete, or execute operations.
From the tool's definition Tool name 'memory.export' and description 'Export all your memories as encrypted blobs' indicate data retrieval with no modification. The verb 'export' denotes reading/extracting data rather than creating, modifying, or deleting it.
Attacks that exploit this kind of access
Export all your memories as encrypted blobs. For migration to. It is categorised as a Read tool in the Sylex Memory MCP Server, which means it retrieves data without modifying state.
Register the Sylex Memory MCP server in PolicyLayer and add a rule for memory.export: 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 Sylex Memory. Nothing to install.
memory.export 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.export 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.export. 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.export is provided by the Sylex Memory MCP server (mastadoonprime/sylex-memory). 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 →