Enumerate every device on a controller grouped by type (zones, flow meters, moisture/temperature/pressure sensors, master valves, pumps, rain gauges, event switches). Each entry includes the
AI agents call baseline_list_devices to retrieve information from Baseline without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists device information from an irrigation controller without any ability to modify, delete, or execute actions. It is a pure read operation. Severity is low because device enumeration poses minimal risk—it reveals system structure but cannot directly harm irrigation operations or cause financial loss. The read-only constraint of the server further confirms this classification.
From the tool's definition Tool name 'baseline_list_devices' and description 'Enumerate every device on a controller' indicate data retrieval. Server description explicitly states 'read-only interaction'. Tool returns device listings with no modification capability.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Enumerate every device on a controller grouped by type (zones, flow meters, moisture/temperature/pressure sensors, master valves, pumps, rain gauges, event switches). Each entry includes the. It is categorised as a Read tool in the Baseline MCP Server, which means it retrieves data without modifying state.
Register the Baseline MCP server in PolicyLayer and add a rule for baseline_list_devices: 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 Baseline. Nothing to install.
baseline_list_devices 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 baseline_list_devices 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 baseline_list_devices. 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.
baseline_list_devices is provided by the Baseline MCP server (swannman/baseline-irrigation-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 →