AI agents call baseline_get_programs 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 configuration and operational data from an irrigation controller without side effects. It queries program details and scheduling information for informational purposes only. The read-only nature of the server and consistency with similar 'get' and 'list' tools confirm this is a safe data retrieval operation with minimal risk.
From the tool's definition Tool name includes 'get' and description states 'List watering programs' with retrieval of status information (last start/finish, duration, water used, next scheduled start). No modification, deletion, or execution of commands indicated.
Attacks that exploit this kind of access
List watering programs for a controller with their last start/finish, duration, water used, next scheduled start/finish, and assigned zones. Sourced from the controller config. 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_get_programs: 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_get_programs 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_get_programs 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_get_programs. 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_get_programs 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 →