List automations
AI agents call abode_list_automations to retrieve information from Garza Home MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves automation configurations from the Abode home security system. Listing automations has no side effects—it queries state without creating, modifying, executing, or destroying data. Even in a home automation context where automations can trigger physical actions, merely listing them poses minimal risk compared to tools like abode_trigger_automation (Execute) or abode_set_mode (Write).
From the tool's definition Tool name 'abode_list_automations' combined with description 'List automations' indicates a query/retrieval operation.
Attacks that exploit this kind of access
List automations. It is categorised as a Read tool in the Garza Home MCP MCP Server, which means it retrieves data without modifying state.
Register the Garza Home MCP server in PolicyLayer and add a rule for abode_list_automations: 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 Garza Home MCP. Nothing to install.
abode_list_automations 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 abode_list_automations 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 abode_list_automations. 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.
abode_list_automations is provided by the Garza Home MCP server (itsablabla/garza-home-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 →