AI agents use archive_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 state (is_active = 0) rather than permanently deleting data, qualifying it as Write rather than Destructive. The reversibility—toggling a flag rather than data erasure—and the fact that the record remains in the database mean an agent could theoretically recover the todo by reversing the flag.
From the tool's definition Soft-delete a todo (sets is_active = 0). The tool modifies data by toggling an is_active flag rather than permanently destroying records, making it a reversible write operation.
Attacks that exploit this kind of access
Soft-delete a todo (sets is_active = 0). 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 archive_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.
archive_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 archive_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 archive_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.
archive_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.
archive_todo is one line of Jikan's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →