AI agents use todo_update to create or update resources in Todo MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todo MCP environment.
The tool creates or modifies data reversibly—it updates task metadata like completion status, priority, tags, or due dates. These changes can be undone by subsequent updates. It does not delete data (Destructive), execute code (Execute), or involve financial transactions (Financial). Severity is low because the blast radius of misuse is confined to task data that is easily correctable.
From the tool's definition Tool description states 'edit an existing todo', which is a modification operation. Sibling tools include 'todo_add' (Write), 'todo_delete' (Destructive), and 'todo_list' (Read), positioning 'todo_update' as a reversible data modification.
Attacks that exploit this kind of access
Use this when the user wants to edit an existing todo. It is categorised as a Write tool in the Todo MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todo MCP server in PolicyLayer and add a rule for todo_update: 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 Todo MCP. Nothing to install.
todo_update 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 todo_update 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 todo_update. 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.
todo_update is provided by the Todo MCP server (peterfabakker/todo-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 →