AI agents use update_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 modifies existing task data reversibly without deleting it or executing arbitrary code. It falls squarely in the Write category (create, update, post, upload). Severity is low because: (1) changes are reversible via another update, (2) blast radius is limited to a single task's metadata, and (3) no data is destroyed or code executed.
From the tool's definition Tool name 'update_todo' and server description states it 'update[s]' todos. The Korean description '기존 일정을 수정합니다' translates to 'Modify/update existing schedule/tasks,' confirming write semantics.
Attacks that exploit this kind of access
기존 일정을 수정합니다. 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 update_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.
update_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 update_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 update_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.
update_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 →