AI agents use archive_all_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 performs bulk state modification on inbox items. While not creating new content (Write) or permanently deleting data (Destructive), it irreversibly changes the read status of potentially many messages at once. This qualifies as Write with medium severity due to the bulk nature and potential loss of visibility into unread items.
From the tool's definition archive_all_inbox: marking inbox messages as read in bulk. The description in Japanese translates to 'mark all inbox items as read'. This modifies the state of multiple inbox items irreversibly (messages cannot be unread), affecting their read status.
Attacks that exploit this kind of access
受信トレイを一括既読にします. 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 archive_all_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.
archive_all_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 archive_all_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 archive_all_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.
archive_all_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 →