AI agents use mark_inbox_seen_bulk 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 modifies data (message read status) reversibly rather than retrieving it (Read), executing arbitrary operations (Execute), or permanently deleting data (Destructive). Bulk operations do not elevate the severity since marking messages as seen is a benign metadata update with no side effects beyond the intended state change. Low severity reflects minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'mark_inbox_seen_bulk' indicates modification of message state (marking as seen), and description states it marks 'multiple inbox messages as seen'. This is a state change operation that is reversible (messages can be marked unseen again).
Attacks that exploit this kind of access
Mark multiple inbox messages as seen in one call. 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 mark_inbox_seen_bulk: 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_seen_bulk 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_seen_bulk 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_seen_bulk. 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_seen_bulk 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 →