AI agents call get_inbox_unread_count to retrieve information from Repsona without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the count of unread messages in an inbox. It performs a read-only operation with no modification, creation, deletion, or execution of external operations. The data retrieved is metadata about message state, making it low severity with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'get_inbox_unread_count' and description '受信トレイの未読件数を取得します' (retrieves unread count from inbox) indicate a query operation that retrieves data without side effects.
Attacks that exploit this kind of access
受信トレイの未読件数を取得します. It is categorised as a Read tool in the Repsona MCP Server, which means it retrieves data without modifying state.
Register the Repsona MCP server in PolicyLayer and add a rule for get_inbox_unread_count: 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.
get_inbox_unread_count is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_inbox_unread_count 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 get_inbox_unread_count. 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.
get_inbox_unread_count 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 →