AI agents use update_inbox to create or update resources in Repsona — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Repsona environment.
This tool modifies inbox item state (marking items as read or unread), which is a reversible data change. It does not delete data (so not Destructive), does not execute code or commands (so not Execute), and does not involve financial operations (so not Financial). It falls cleanly into Write category as a state update operation.
From the tool's definition Tool name: update_inbox. Description: 受信トレイの未読・既読を更新します (Update read/unread status of items in the inbox). The action updates metadata state (read/unread flags) without creating, deleting, or executing code.
Attacks that exploit this kind of access
受信トレイの未読・既読を更新します. It is categorised as a Write tool in the Repsona MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Repsona MCP server in PolicyLayer and add a rule for update_inbox: 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 Repsona. Nothing to install.
update_inbox 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 update_inbox 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 update_inbox. 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.
update_inbox is provided by the Repsona MCP server (@bellx2/repsona-mcp-server). 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 →