ha_render_template · Hass MCP: Risk & Policy

WHAT IT DOES

What ha_render_template does on Hass

AI agents invoke ha_render_template to trigger actions in Hass. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why ha_render_template needs a policy

Rendering a Jinja2 template is an execution action: the template engine evaluates code/expressions server-side. While it primarily returns a result (read-like), Jinja2 templates can call functions, access system state, and potentially trigger side effects depending on the Home Assistant template environment. This qualifies as Execute rather than Read due to the arbitrary code evaluation aspect.

From the tool's definition 'Render a Jinja2 template and return the result' — executing a template engine processes arbitrary template code which can invoke filters, functions, and expressions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ha_render_template Rate-limited

ha_render_template stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ha_render_template": {
      "limits": [
        {
          "counter": "ha_render_template_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Hass, so you can run agents against it safely.

FAQ

Questions about ha_render_template

What does the ha_render_template tool do? +

Render a Jinja2 template and return the result. It is categorised as a Execute tool in the Hass MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ha_render_template? +

Register the Hass MCP server in PolicyLayer and add a rule for ha_render_template: 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 Hass. Nothing to install.

What risk level is ha_render_template? +

ha_render_template is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ha_render_template? +

Yes. Add a rate_limit block to the ha_render_template 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.

How do I block ha_render_template completely? +

Set action: deny in the PolicyLayer policy for ha_render_template. 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.

What MCP server provides ha_render_template? +

ha_render_template is provided by the Hass MCP server (thewhykiki/hass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.