Browse memory contents. Without a namespace: shows all namespaces with entry counts and last_activity_at (demo/* and completed task-run namespaces hidden by default). With a namespace: shows all state keys, log count, and the 5 most recent log entry previews.\n\nIf this is your first memory opera...
AI agents call memory_list to retrieve information from Munin Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_list performs information retrieval and inspection of stored memory data without any ability to create, modify, delete, or execute operations. It is purely a query/list operation, fitting the Read category definition of 'retrieves or queries data; no side effects'.
From the tool's definition The tool description explicitly states it 'Browse memory contents', 'shows all namespaces', and 'shows all state keys... and previews'. These are retrieval operations with no modification capability. The word 'browse' and 'shows' indicate read-only access.
Attacks that exploit this kind of access
Browse memory contents. Without a namespace: shows all namespaces with entry counts and last_activity_at (demo/* and completed task-run namespaces hidden by default). With a namespace: shows all state keys, log count, and the 5 most recent log entry previews.\n\nIf this is your first memory operation in this conversation, call memory_orient first. It is categorised as a Read tool in the Munin Memory MCP Server, which means it retrieves data without modifying state.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_list: 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 Munin Memory. Nothing to install.
memory_list 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_list 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_list. 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_list is provided by the Munin Memory MCP server (magnus-gille/munin-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 →