AI agents call list_agents to retrieve information from ATMcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves team status information. It performs no mutations, executions, deletions, or financial operations. The information retrieved (presence, status, progress) is read-only monitoring data used for dashboard display and coordination visibility. Even in a multi-agent system context, listing agent status is a benign read operation with minimal blast radius if misused.
From the tool's definition Tool name 'list_agents' and description 'Team roster with derived presence (healthy/degraded/offline), status, and progress' indicate retrieval of status information without modification or side effects.
Attacks that exploit this kind of access
Team roster with derived presence (healthy/degraded/offline), status, and progress. It is categorised as a Read tool in the ATMcp MCP Server, which means it retrieves data without modifying state.
Register the AT MCP server in PolicyLayer and add a rule for list_agents: 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 ATMcp. Nothing to install.
list_agents 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 list_agents 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 list_agents. 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.
list_agents is provided by the AT MCP server (midcheck/atmcp). 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 →