AI agents use mark_inbox_done 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.
The tool appears to update the status of inbox items (likely setting a 'done' flag), which is a reversible modification. This qualifies as Write rather than Destructive since marking done does not irreversibly delete data. Severity is medium because misuse could cause workflow confusion if items are incorrectly marked complete, but the operation is reversible via uncompleting or other corrections.
From the tool's definition Tool name 'mark_inbox_done' suggests marking an inbox item as complete/done, which modifies state reversibly. Server context indicates it manages behavioral tracking sessions and todo items.
Attacks that exploit this kind of access
mark_inbox_done. 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 mark_inbox_done: 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.
mark_inbox_done 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 mark_inbox_done 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 mark_inbox_done. 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.
mark_inbox_done 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 →