List connected messaging accounts
AI agents call beeper_get_accounts 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 and enumerates information about connected accounts without modifying, executing, or deleting any data. It is a straightforward read operation on account metadata. The blast radius is minimal—an agent listing accounts cannot cause harm beyond potential information disclosure, which is low-severity in a personal home automation context where the server is already trusted infrastructure.
From the tool's definition Tool name 'beeper_get_accounts' with description 'List connected messaging accounts' indicates a retrieval operation with the verb 'List', which is non-destructive query functionality.
Attacks that exploit this kind of access
List connected messaging accounts. 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 beeper_get_accounts: 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.
beeper_get_accounts 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 beeper_get_accounts 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 beeper_get_accounts. 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.
beeper_get_accounts 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 →