error_log_get
AI agents call error_log_get to retrieve information from Homeassistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' suffix and 'error_log' prefix strongly suggest this tool retrieves or queries error log data without modifying or executing operations. While the empty description reduces certainty, the name alone indicates a Read operation with minimal blast radius—accessing logs does not affect system state or trigger actions.
From the tool's definition Tool name 'error_log_get' indicates a retrieval operation ('get') on log data ('error_log'). No description provided, but naming convention suggests read-only access to historical error logs.
Attacks that exploit this kind of access
error_log_get. It is categorised as a Read tool in the Homeassistant MCP Server, which means it retrieves data without modifying state.
Register the Homeassistant MCP server in PolicyLayer and add a rule for error_log_get: 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 Homeassistant. Nothing to install.
error_log_get 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 error_log_get 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 error_log_get. 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.
error_log_get is provided by the Homeassistant MCP server (robbrad/homeassistant-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 →