Packaged as a Home Assistant add-on that exposes a tool to forward JSON reports to Power Automate webhooks, enabling integration between Home Assistant automation and Microsoft Power Automate workflows.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Home Assistant MCP Reporter post a report with temperature 72°F and humidity 45%"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This repository contains a minimal Python MCP server packaged as a Home Assistant add-on.
The server exposes one MCP tool:
postReport
postReport accepts a JSON object and forwards it to the configured Power Automate webhook.
Related MCP server: hass-mcp
The add-on requires an API key configured from the Home Assistant add-on config page.
Send the API key in either of these headers when calling the MCP endpoint:
X-API-Key: <your-key>
Authorization: Bearer <your-key>
python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -e .
python -m mcp_reporter_serverThe server listens on 0.0.0.0:8099 using streamable HTTP transport at /.
For discovery, the server also exposes authenticated tool-list endpoints at:
GET /tools
POST /tools
Add this repository as an add-on repository in Home Assistant.
Install the MCP Reporter add-on.
Start the add-on.
Connect your MCP client to http://homeassistant.local:8099/ or the add-on host/IP on port 8099.
The webhook URL is baked in by default to match the requested behavior.
You can override it with the POWER_AUTOMATE_WEBHOOK_URL environment variable if needed.
This server cannot be deployed
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.
POC MCP server. Tool say_hello returns 'Welcome' (agent -> MCP -> API path).
