AI agents call inbox_status to retrieve information from Agent Bus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only inspection of message state within a local agent collaboration system. It retrieves information about inbox status but does not modify, execute, delete, or consume any messages.
From the tool's definition Tool description explicitly states 'Inspect an agent inbox without consuming messages' and 'Shows unread, claimed/in-flight, recent delivered messages'. The verb 'inspect' and qualifier 'without consuming' indicate a non-destructive query operation.
Attacks that exploit this kind of access
Inspect an agent inbox without consuming messages. Shows unread, claimed/in-flight, recent delivered messages, and a clear summary. It is categorised as a Read tool in the Agent Bus MCP Server, which means it retrieves data without modifying state.
Register the Agent Bus MCP server in PolicyLayer and add a rule for inbox_status: 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 Agent Bus. Nothing to install.
inbox_status 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 inbox_status 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 inbox_status. 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.
inbox_status is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →