AI agents use create_todo to create or update resources in Mcp Todo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Todo environment.
This tool creates new todo items, which is a reversible write operation. It modifies state by adding records but does not delete, destroy, or execute arbitrary code. Severity is medium because a compromised agent could spam or pollute the task list, but the operation is reversible via delete_todo. Not critical since it only adds data without financial, destructive, or execution side effects.
From the tool's definition Tool name 'create_todo' and server description states it 'allow users to list, create, update, and delete todos and notes'. The Korean description '새로운 일정을 생성합니다' translates to 'Creates a new schedule/task'. This is a create operation that adds new data.
Attacks that exploit this kind of access
새로운 일정을 생성합니다. It is categorised as a Write tool in the Mcp Todo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Todo MCP server in PolicyLayer and add a rule for create_todo: 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.
create_todo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_todo 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 create_todo. 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.
create_todo 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 →