api_info
AI agents call api_info 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 naming convention, 'api_info' most likely retrieves or queries API information/metadata from Home Assistant without side effects. However, the empty description prevents higher confidence. The context of other tools on this server (control, access, call_service) suggests this is a passive information tool. Categorized as Read with low severity due to minimal blast radius if misused.
From the tool's definition Tool name 'api_info' suggests information retrieval; no verb indicating modification, deletion, or execution. Description is empty, limiting confidence.
Attacks that exploit this kind of access
api_info. 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 api_info: 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.
api_info 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 api_info 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 api_info. 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.
api_info 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 →