AI agents call baseline_get_live 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 current sensor/status data from an irrigation controller device. It performs a query operation with no side effects, state changes, or ability to modify system configuration. The read-only nature of the server and all sibling tools (get_*, list_*) further confirms this is a safe data retrieval operation.
From the tool's definition Tool description states 'Current live reading' and server description emphasizes 'read-only interaction'. Tool retrieves instantaneous data from an enumerated device without modifying any state.
Attacks that exploit this kind of access
Current live reading for one enumerated device, by its reporting serial (from baseline_list_devices: serialNumber, or decoderSN for a zone). 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_live: 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_live 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_live 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_live. 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_live 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 →