Search messages by content (case-insensitive).
AI agents call msg_search 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 searches existing messages without creating, modifying, deleting, or executing any operations. It is a passive information retrieval mechanism, placing it firmly in the Read category. The low severity reflects minimal blast radius—misuse would only expose message content the agent already has permissions to access, not modify or destroy data or trigger external effects.
From the tool's definition Tool name 'msg_search' and description 'Search messages by content' indicate a read-only query operation with no data modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Search messages by content (case-insensitive). 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_search: 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_search 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_search 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_search. 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_search 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 →