AI agents call message_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.
The tool retrieves and reports status information about messages on a local agent bus without modifying, executing, or deleting anything. It is a diagnostic/introspection function that observes message state in a shared collaboration system. No creation, modification, deletion, code execution, or financial operations are implied.
From the tool's definition Tool name 'message_status' and description indicate it 'diagnose[s]' message state by retrieving delivery/claim state, reply, recipient presence, task metadata, and suggested actions. These are all read-only diagnostic queries with no side effects.
Attacks that exploit this kind of access
Diagnose one message: delivery/claim state, reply, recipient presence, related task, and suggested next actions. 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 message_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.
message_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 message_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 message_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.
message_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 →