memory_store_list
AI agents call memory_store_list to retrieve information from Managed Agent Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming pattern 'list' aligns with Read category operations that retrieve or query data with no side effects. The empty description reduces confidence slightly, but the verb 'list' is unambiguously associated with read-only retrieval. Given the server's focus on observing and interacting with managed agents, this tool likely returns memory store contents for inspection without altering them.
From the tool's definition Tool name 'memory_store_list' indicates a list/query operation. The description is empty, limiting confidence, but 'list' strongly suggests retrieval of stored memory data without modification.
Attacks that exploit this kind of access
memory_store_list. It is categorised as a Read tool in the Managed Agent Control MCP Server, which means it retrieves data without modifying state.
Register the Managed Agent Control MCP server in PolicyLayer and add a rule for memory_store_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 Managed Agent Control. Nothing to install.
memory_store_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_store_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_store_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_store_list is provided by the Managed Agent Control MCP server (modus-agendi/managed-agent-control-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 →