← Back to Skills Marketplace
dsnkzdeny

Homeassistant Mcp

by dsnkzdeny · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
99
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install homeassistant-mcp
Description
Provides structured access to Home Assistant devices, sensors, and cameras via MCP, with specific handling for cameras, garage doors, and device control.
README (SKILL.md)

Home Assistant MCP Skill

Description

This skill provides structured access to Home Assistant via its native MCP (Model Context Protocol) integration. It provides tools and context for interacting with devices, sensors, and cameras in the smart home.

Credentials

The MCP server endpoint is http://220.0.0.5:8123/api/mcp. Ensure the connection is configured with the correct Long-Lived Access Token.

Best Practices

  1. Camera Snapshots: MCP tools for cameras (video_garage, homeassistant___XXXXX) DO NOT WORK! Always use exec with curl to the REST API to get camera snapshots: curl -s -H "Authorization: Bearer \x3CTOKEN>" "http://220.0.0.5:8123/api/camera_proxy/camera.\x3Centity_id>" -o /home/clawd/.openclaw/workspace/\x3Cfilename>.jpg After fetching, verify it's a JPEG with file, then display it using the MEDIA:\x3Cpath> directive.

  2. Garage Operations:

    • The garage ESPHome logic is inverted: HassTurnOff = OPEN, HassTurnOn = CLOSE.
    • Wait 30-50 seconds after a command before checking the position.
    • True garage door position is determined by endstops, not just current_position: 0 or state.
    • Ignore Garage 2 Motion as it produces false positives.

  3. Device Control:

    • NEVER turn devices on or off without explicit user request.
    • Do not use the homeassistant__forced tool.

  4. Status Checks:

    • Use homeassistant__GetLiveContext to get a snapshot of all exposed entities.
    • If MCP tools timeout, fallback to the REST API: curl -H "Authorization: Bearer \x3CTOKEN>" http://220.0.0.5:8123/api/states/\x3Centity_id>

Key Entities

Review /home/clawd/.openclaw/workspace/memory/home-assistant-entities.md for a full list of areas and key entities.

Usage Guidance
Install only if you recognize and control the Home Assistant endpoint shown in the skill. Before using it, confirm the token, network path, and entity memory file are safe, and require explicit user confirmation for any device or garage-door operation.
Capability Analysis
Type: OpenClaw Skill Name: homeassistant-mcp Version: 1.0.0 The skill instructions in SKILL.md direct the AI agent to bypass standard MCP tools and instead use the 'exec' capability to run 'curl' commands for camera snapshots and status checks. This pattern involves handling sensitive Long-Lived Access Tokens within shell commands and writing files to the workspace, which increases the risk of token exposure and command injection. While these instructions appear to be functional workarounds for technical limitations, the reliance on raw shell execution for API interactions at the IP 220.0.0.5 is a high-risk practice.
Capability Tags
requires-oauth-tokenrequires-sensitive-credentials
Capability Assessment
ℹ Purpose & Capability
The Home Assistant device, sensor, camera, and garage-door capabilities match the stated purpose, but they include sensitive camera access and physical-device control.
⚠ Instruction Scope
The instructions tell the agent to use exec/curl REST calls with a bearer token as a fallback or replacement for MCP tools, which is a broad escape hatch for a sensitive smart-home integration.
ℹ Install Mechanism
This is instruction-only with no code or install script. However, registry metadata declares no primary credential or required env var while SKILL.md requires a Home Assistant Long-Lived Access Token.
⚠ Credentials
The Home Assistant endpoint is hard-coded as an HTTP address rather than a user-configured, clearly private, or HTTPS endpoint, making the credential and data boundary hard to verify.
ℹ Persistence & Privilege
No background persistence code is present, but the skill relies on a long-lived token and a persistent local memory file containing Home Assistant entity information.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install homeassistant-mcp
  3. After installation, invoke the skill by name or use /homeassistant-mcp
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Home Assistant MCP Skill 1.0.0 - Initial release providing structured access to Home Assistant via Model Context Protocol (MCP). - Enables interaction with devices, sensors, and cameras in the smart home environment. - Documents credential setup using server endpoint and access token. - Clarifies camera snapshot handling with REST API instead of MCP tools. - Notes specific logic for garage door operations and position checks. - Outlines device control best practices and fallback methods for status checks. - References external documentation for a complete entity list.
Metadata
Slug homeassistant-mcp
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Homeassistant Mcp?

Provides structured access to Home Assistant devices, sensors, and cameras via MCP, with specific handling for cameras, garage doors, and device control. It is an AI Agent Skill for Claude Code / OpenClaw, with 99 downloads so far.

How do I install Homeassistant Mcp?

Run "/install homeassistant-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Homeassistant Mcp free?

Yes, Homeassistant Mcp is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Homeassistant Mcp support?

Homeassistant Mcp is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Homeassistant Mcp?

It is built and maintained by dsnkzdeny (@dsnkzdeny); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments