AI agents call get_agent_output 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 retrieves and queries output logs from other agents in the multi-agent system. The 'tail' operation is a read-only query of historical output data. There is no capability to modify, delete, or execute actions—it merely fetches information. The blast radius if misused is limited to information disclosure, making this a low-severity Read action.
From the tool's definition Tool name 'get_agent_output' and description 'Tail another agent's output' indicates retrieval of existing data with no modification or side effects.
Attacks that exploit this kind of access
Tail another agent's output (by display_name or agent_id) from since_seq. With. 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 get_agent_output: 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.
get_agent_output 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 get_agent_output 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 get_agent_output. 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.
get_agent_output 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 →