AI agents use uncomplete_todo to create or update resources in Jikan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jikan environment.
This tool modifies the state of a todo item by removing its completion status for today. This is a Write operation because it reversibly changes data. Severity is low because: (1) the change is easily reversible (the todo can be completed again), (2) the blast radius is limited to a single user's todo item, and (3) no permanent data loss or financial impact occurs.
From the tool's definition Tool description explicitly states 'Remove a todo completion' which is a modification operation. The action is reversible and non-destructive (a todo can be marked complete again). No data is deleted or destroyed, only the completion status is reverted.
Attacks that exploit this kind of access
Remove a todo completion for today. Free (0 credits). It is categorised as a Write tool in the Jikan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jikan MCP server in PolicyLayer and add a rule for uncomplete_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 Jikan. Nothing to install.
uncomplete_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 uncomplete_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 uncomplete_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.
uncomplete_todo is provided by the Jikan MCP server (thunderrabbit/jikan). 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 →