@diegobit
Basic information
SImple MCP server to manage your aranet4 device and local db.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"aranet4": {
"command": "{{PATH_TO_UV}}",
"args": [
"--directory",
"{{PATH_TO_SRC}}/aranet4-mcp-server/",
"run",
"src/server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
aranet4-mcp-server is an MCP server that manages your Aranet4 CO₂ sensor. It scans nearby devices, fetches new data from the sensor's embedded memory, saves measurements to a local SQLite database, and allows querying recent or historical data—including optional visualizations. Built on the Aranet4-Python library, it is intended for users who want to monitor and track air quality through MCP-compatible clients.
Clone the repository, prepare the environment (recommended with uv, alternative with pip install .), and add the server to your MCP client configuration (e.g., Claude Desktop or Cursor). After installation, start your client and ask init aranet4 for guided configuration, or manually edit config.yaml with the device's MAC address. Use the fetch_new_data tool to update the database, and query data with get_recent_data or get_data_by_timerange. Optionally, set up a cron job or LaunchAgent for automatic periodic fetching.
init aranet4 commandaranet4-mcp-server includes MCP integration for use with MCP clients. For a pure Python version without MCP logic, see the separate [aranet4-archiver](https://github.com/diegobit/aranet4-archiver) project.
The server depends on the [Aranet4-Python](https://github.com/Anrijs/Aranet4-Python) library. Using `uv` is recommended; with `pip`, run `pip install .` inside the cloned repository.
All data is stored locally in a SQLite database created by the server. No external cloud service is required.
Yes, for MCP clients that support images, you can ask for a plot when querying recent or historical data. The server will generate and display it.
You can set up a cron job (any platform) or a LaunchAgent (macOS) to run `fetch-job.py` periodically. An example plist file is included in the repository.
Open-source MCP to use Blender with any LLM
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Comments