[Admin] Fetch a raw memory object by UUID — all fields including internal metadata. Uses the Firestore index to resolve which collection the memory lives in. Optionally includes the vector embedding. Requires admin access (ADMIN_USER_IDS).
AI agents call remember_admin_inspect_memory to retrieve information from Remember without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data without side effects, fitting the Read category. Severity is high because: (1) it operates on a multi-tenant memory system where data isolation is critical; (2) it exposes 'all fields including internal metadata' which could include sensitive user information; (3) admin-only access indicates privileged information access; (4) potential for unauthorized disclosure if admin credentials are…
From the tool's definition Tool description states 'Fetch a raw memory object by UUID — all fields including internal metadata' and 'Requires admin access (ADMIN_USER_IDS)'. The action is retrieval-only ('Fetch'), with no modification or deletion.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
[Admin] Fetch a raw memory object by UUID — all fields including internal metadata. Uses the Firestore index to resolve which collection the memory lives in. Optionally includes the vector embedding. Requires admin access (ADMIN_USER_IDS). It is categorised as a Read tool in the Remember MCP Server, which means it retrieves data without modifying state.
Register the Remember MCP server in PolicyLayer and add a rule for remember_admin_inspect_memory: 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 Remember. Nothing to install.
remember_admin_inspect_memory 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 remember_admin_inspect_memory 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 remember_admin_inspect_memory. 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.
remember_admin_inspect_memory is provided by the Remember MCP server (@prmichaelsen/remember-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 →