Get messages for an agent. Filter by unread/read/archived.
AI agents call msg_inbox to retrieve information from Agent Messaging without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing messages with optional filtering. It has no side effects—reading messages does not modify state, execute code, or trigger external actions.
From the tool's definition Tool name 'msg_inbox' and description 'Get messages for an agent' indicate a retrieval operation with filter parameters (unread/read/archived). No creation, modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Get messages for an agent. Filter by unread/read/archived. It is categorised as a Read tool in the Agent Messaging MCP Server, which means it retrieves data without modifying state.
Register the Agent Messaging MCP server in PolicyLayer and add a rule for msg_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 Messaging. Nothing to install.
msg_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 msg_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 msg_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.
msg_inbox is provided by the Agent Messaging MCP server (rumblingb/agent-messaging-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
msg_inbox is one line of Agent Messaging's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →