AI agents call inbox 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 allows retrieval of incoming messages but does not modify, execute, delete, or trigger financial operations. The operation is passive and informational. Within a local agent collaboration server, reading one's own inbox poses minimal risk—the worst case is information disclosure of messages already addressed to the agent. Confidence is high because the description is explicit and unambiguous.
From the tool's definition Tool description explicitly states 'Read new messages' — a retrieval operation with no side effects. Consistent with the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'.
Attacks that exploit this kind of access
Read new messages addressed to you. 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: 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 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 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. 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 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 →