config_check
AI agents call config_check 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.
Based on the name alone, this tool likely performs a read-only check of Home Assistant configuration without modifying state or executing commands. The empty description prevents higher confidence, but the pattern matches diagnostic/inspection tools common in home automation systems. If it were destructive or executable, the name would typically indicate that (e.g., 'config_reset', 'config_apply').
From the tool's definition Tool name 'config_check' suggests validation or inspection of configuration state; no side-effects implied by the name. Description is empty, reducing confidence.
Attacks that exploit this kind of access
config_check. 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 config_check: 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.
config_check 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 config_check 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 config_check. 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.
config_check 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 →