Queue a tenant data export (R4, 1 approver). Generates an encrypted dump file
AI agents call tenant_export_secure to retrieve information from Celiums Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exports tenant data into an encrypted dump file — it reads and exfiltrates potentially all data for a tenant. While it does not delete or modify data, the blast radius is high because a malicious or mistaken invocation could exfiltrate the entire tenant's memory/knowledge store. The 'R4, 1 approver' notation suggests a regulated/sensitive data classification.
From the tool's definition Queue a tenant data export (R4, 1 approver). Generates an encrypted dump file
Documented attack patterns abuse exactly the kind of access tenant_export_secure gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Celiums Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for tenant_export_secure:
{
"version": "1",
"default": "deny",
"tools": {
"tenant_export_secure": {}
}
}tenant_export_secure 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.
Queue a tenant data export (R4, 1 approver). Generates an encrypted dump file. It is categorised as a Read tool in the Celiums Memory MCP Server, which means it retrieves data without modifying state.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for tenant_export_secure: 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 Celiums Memory. Nothing to install.
tenant_export_secure 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 tenant_export_secure 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 tenant_export_secure. 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.
tenant_export_secure is provided by the Celiums Memory MCP server (terrizoaguimor/celiums-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Celiums Memory, 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.
62 Celiums Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.