AI agents call agent_health to retrieve information from Atlas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system state information (health status and configuration) without side effects. It is a diagnostic/monitoring function that does not create, modify, delete, or execute operations. This is a canonical Read operation with minimal security risk—even if misused, it only exposes system metadata rather than enabling destructive or unauthorized actions.
From the tool's definition Tool name 'agent_health' and description 'Check agent health status and configuration' indicate a query/monitoring operation. No modification, deletion, code execution, or financial operation is performed.
Attacks that exploit this kind of access
Check agent health status and configuration. It is categorised as a Read tool in the Atlas MCP Server, which means it retrieves data without modifying state.
Register the Atlas MCP server in PolicyLayer and add a rule for agent_health: 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 Atlas. Nothing to install.
agent_health 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 agent_health 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 agent_health. 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.
agent_health is provided by the Atlas MCP server (rsanandres/atlas_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 →