AI agents call list_memos to retrieve information from Mcp Todo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing memo data without modifying, deleting, or executing any operations. It is purely a read operation that returns information. The blast radius of misuse is minimal—an agent could only enumerate memos the user already has access to, posing no risk of data loss, execution, or financial harm.
From the tool's definition Tool name 'list_memos' and description indicating it retrieves/queries a list of memos sorted by recent modification date. The Korean description '메모 목록을 조회합니다. 최근 수정순으로 정렬됩니다.' translates to 'Lists memos.
Attacks that exploit this kind of access
메모 목록을 조회합니다. 최근 수정순으로 정렬됩니다. It is categorised as a Read tool in the Mcp Todo MCP Server, which means it retrieves data without modifying state.
Register the Mcp Todo MCP server in PolicyLayer and add a rule for list_memos: 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 Mcp Todo. Nothing to install.
list_memos 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 list_memos 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 list_memos. 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.
list_memos is provided by the Mcp Todo MCP server (moon-daeseung/mcp-todo). 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 →