AI agents use update_checklist_item to create or update resources in Todo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todo environment.
This tool modifies an existing checklist item's state (e.g., text, completion status) but does not permanently delete it. The change is reversible—the item can be updated again or reverted. This qualifies as Write rather than Destructive. Severity is medium because misuse could corrupt a user's task list, but the impact is limited to a single item and reversible.
From the tool's definition Tool name 'update_checklist_item' and description 'Update a checklist item' explicitly indicate modification of existing data. Server description confirms 'full CRUD operations' on Microsoft To Do tasks.
Attacks that exploit this kind of access
Update a checklist item. It is categorised as a Write tool in the Todo 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 update_checklist_item: 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. Nothing to install.
update_checklist_item 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_checklist_item 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_checklist_item. 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_checklist_item is provided by the Todo MCP server (jc1122/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 →