AI agents use mark_inbox_seen 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 performs a state modification (marking a message as seen) which is typical Write category behavior. The operation is reversible (a message can be marked unseen again) and has minimal blast radius. Even if an AI agent marks all inbox messages as seen, the underlying messages remain intact and the action can be undone.
From the tool's definition Tool name is 'mark_inbox_seen' with description 'Mark an inbox message as seen.' This operation modifies the state of an inbox message from unseen to seen, which is a reversible state change.
Attacks that exploit this kind of access
Mark an inbox message as seen. 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: 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 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 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. 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 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 →