// MCP TOOL REFERENCE

HA TOOLS

11 tools from the Ha MCP Server, categorised by risk level.

// ALL 11 HA TOOLS

READ 2 tools

Read scene_list List all scenes from Home Assistant Read scene_show_lights SAFE read-only tool. Shows ALL Home Assistant lights with FULL details. Does NOT change anything. Use this ...

WRITE 8 tools

Write scene_activate Activate a scene in Home Assistant. REQUIRES user_confirmed=true - user must explicitly request scene activ... Write scene_adjust_light PREFERRED for controlling lights. Turn on/off, set brightness (0-100%), RGB color, color temperature (Kelvi... Write scene_blackout Turn off ALL lights. Optionally create/update a 'Blackout' scene. REQUIRES user_confirmed=true - user must ... Write scene_configure Configure the Home Assistant connection for the Scene MCP server. Required before using other scene_ tools ... Write scene_create Create a NEW scene in Home Assistant. ONLY call when user EXPLICITLY asks to create/save a NEW scene. Befor... Write scene_diagnose Diagnose lights and scenes. Tests connectivity, response times, identifies problems with scenes (null value... Write scene_fix Fix problems found by scene_diagnose. Can fix null values, add missing lights to exclusive scenes, restore ... Write scene_update Update an existing scene with current light states. ONLY call this when user EXPLICITLY asks to save/update...

DESTRUCTIVE 1 tools

Destructive scene_delete Delete a scene from Home Assistant

// RUNNING THIS SERVER

The managed route: connect Ha through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y ha-mcp-server

// FAQ

How many tools does the Ha MCP server have? +

The Ha MCP server exposes 11 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Ha tools? +

Route the Ha server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Ha tools fall into? +

Ha tools are categorised as Read (2), Write (8), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.