AI agents call get_memo 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 performs a read-only query operation to fetch memo data. It has no side effects—it neither modifies, deletes, nor executes anything. Even if misused by an AI agent, the worst outcome is information disclosure of existing memos, which poses minimal risk in a task/memo management context. Severity is low due to limited blast radius.
From the tool's definition Tool name 'get_memo' and description indicating it retrieves detailed content of a specific memo ('특정 메모의 상세 내용을 조회합니다' = 'retrieves the detailed content of a specific memo'). No modification, deletion, or execution capability.
Attacks that exploit this kind of access
특정 메모의 상세 내용을 조회합니다. 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 get_memo: 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.
get_memo 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 get_memo 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 get_memo. 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.
get_memo 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 →