Export memories to JSON format. Can export all or by category.
AI agents call export_memories to retrieve information from Claude Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Exporting memories reads and serializes data into JSON without modifying or deleting the underlying records. However, the blast radius is medium because exporting 'all' memories could expose sensitive personal/contextual data that Claude has stored persistently across sessions.
From the tool's definition Export memories to JSON format. Can export all or by category.
Attacks that exploit this kind of access
Export memories to JSON format. Can export all or by category. It is categorised as a Read tool in the Claude Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory MCP Server MCP server in PolicyLayer and add a rule for export_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 Claude Memory MCP Server. Nothing to install.
export_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 export_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 export_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.
export_memories is provided by the Claude Memory MCP Server MCP server (seongcheoljeon/claudememorymcp). 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 →