mcp-httc
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., "@mcp-httcset the sanctuary thermostat to 72 degrees"
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.
mcp-httc
MCP server wrapping Honeywell Total Connect Comfort (legacy
mytotalconnectcomfort.com) so John can drive Deer Park UMC's 13
thermostats from any Claude surface.
Sister projects on the same Raspberry Pi: mcp-ui, mcp-google, mcp-pco.
Stack: Python 3.13, FastAPI, FastMCP, AIOSomecomfort, aiohttp.
Backend:
AIOSomecomfort(the same library Home Assistant uses) — the only Python/JS option that keeps up with Honeywell's periodic portal breakages.Transport: Streamable HTTP only; OAuth 2.1 with HS256 JWTs and a shared login password (1:1 port of
mcp-ui's auth model).Deployment: systemd on the Pi, Cloudflare Tunnel ingress at
https://httc.1421mcps.com. Seereferences/2026-04-16_initial-deployment.mdonce the first deploy is written up.
Tools (v1)
Tool | Purpose |
| All devices with current temp, humidity, mode, fan, setpoints, hold state |
| One device by name (case-insensitive) or numeric id |
| Heat and/or cool setpoint with |
| System mode: heat / cool / auto / off |
| Fan: auto / on / circulate |
| Humidity setpoint (only on devices that have a humidifier) |
Schedule read/write and background polling/monitoring are out of scope for v1.
Deploy a code change
git push origin main
ssh 1421mcp 'cd mcp-httc && git pull && \
.venv/bin/pip install -r requirements.txt && \
sudo systemctl restart mcp-httc && \
sudo journalctl -u mcp-httc -f --since "10 seconds ago"'Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
The Ramp MCP server enables users to securely connect Ramp with AI assistants like ChatGPT and Claude to query financial data and take actions using natural language. It transforms Ramp's developer API into a SQL interface that LLMs can query, allowing admins to analyze spend trends, identify cost savings, and run complex SQL analyses on comprehensive datasets (transactions, purchase orders, vendors, users), while all users can manage cards, view transactions, request reimbursements, and get expense policy answers.
Cloud-hosted MCP server for secure AI access to enterprise data sources via CData Connect AI.
MCP server enabling AI agents to manage Bitrix24 features via standardized protocol