Exports complete session data in markdown or JSON format. Includes projects, tasks, memories, and session activity summary.
AI agents call export_session to retrieve information from Memory Pickle MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and serializes existing session data into a portable format (markdown or JSON). It does not modify, delete, or create any data — it only retrieves and formats what already exists. The blast radius is low since it only exposes data already held within the session context, though it could expose sensitive project/task details if misused.
From the tool's definition Exports complete session data in markdown or JSON format. Includes projects, tasks, memories, and session activity summary.
Documented attack patterns abuse exactly the kind of access export_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Pickle MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for export_session:
{
"version": "1",
"default": "deny",
"tools": {
"export_session": {}
}
} export_session is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Exports complete session data in markdown or JSON format. Includes projects, tasks, memories, and session activity summary. It is categorised as a Read tool in the Memory Pickle MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory Pickle MCP server in PolicyLayer and add a rule for export_session: 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 Memory Pickle MCP. Nothing to install.
export_session 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_session 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_session. 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_session is provided by the Memory Pickle MCP server (justar96/memory-pickle). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Pickle MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Memory Pickle MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.