Read full message content. Marks message as read.
AI agents call msg_read 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 and queries message content without creating, modifying, deleting, or executing arbitrary operations. Marking a message as read is a benign metadata update. The tool fits squarely in the Read category with low severity because it only accesses existing data and performs a standard, reversible state change.
From the tool's definition Tool name is 'msg_read' and description states 'Read full message content. Marks message as read.' The primary action is reading/retrieving message data with no destructive or side-effect operations beyond marking as read (a normal state-tracking operation).
Attacks that exploit this kind of access
Read full message content. Marks message as read. 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_read: 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_read 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_read 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_read. 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_read 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.
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 →