Show the current agent identity, namespace, and Obsidian status.
AI agents call memory_who to retrieve information from Agent Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation: it retrieves and displays metadata about the current agent's identity and namespace configuration. While the severity is elevated to 'medium' rather than 'low' because the identity and namespace information could be sensitive in multi-tenant scenarios and might be used to pivot attacks or understand system structure, the tool itself performs no side effects.
From the tool's definition Tool description states it 'Show[s] the current agent identity, namespace, and Obsidian status' — a retrieval operation that queries system state without modifying data.
Attacks that exploit this kind of access
Show the current agent identity, namespace, and Obsidian status. It is categorised as a Read tool in the Agent Memory MCP Server, which means it retrieves data without modifying state.
Register the Agent Memory MCP server in PolicyLayer and add a rule for memory_who: 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 Agent Memory. Nothing to install.
memory_who 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_who 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_who. 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_who is provided by the Agent Memory MCP server (khaled1174/agent-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 →