Remote script. An MCP client that can call PC tools may run actions on the machine, so start with read-only tools and check the N1/N2/N3 levels before granting write access.
Who it is forA developer or power user who already uses an MCP client and wants it to control Jarvis lights and PC tools.
The problemAn AI client has no access to the home or PC controls on the local machine, so it cannot act on them.
The outcomeAn MCP client lists and calls the Jarvis domotique and PC tools through the local MCP server.
What you need first
- Windows 11 PC with a microphone
- Internet access for the installer, which fetches uv, Git, Python 3.13 and Chromium
- An API key from OpenAI or Anthropic if you use cloud mode (not needed for local mode)
- Optional: Philips Hue lights and OBS if you want those tools
Steps
- Install and start Jarvis with
uv syncanduv run playfirst, so the tools are configured. - Find the MCP server entry point in the repository docs or source, since the README does not give the start command. (inferred, check the README)
- Add the MCP server to your client's configuration as a local stdio server. (inferred, check the README)
- Restart the MCP client and check that the Jarvis tools appear in its tool list.
- Ask the client to run one safe tool, such as reading a light state, and confirm the result.
Prompt for your agent
In the sosoj92/jarvis-assistant-vocal repo, find the MCP server start command and register it with <MCP client name>. Expected output: the client lists the Jarvis home and PC tools and one read-only call returns a result. Verify the tool list before reporting success.
Caveat. The README names the MCP server and the clients it supports but does not give the exact start command or client config, so those steps must be checked in the source.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page