@Kevin-0, it should work now,

While testing, I noticed a bug in the login flow that I still need to fix. If login to TRIGGERcmd with Google while adding the TRIGGERcmd MCP server, then click "Continue with Google" it will go to the initial TRIGGERcmd page. It's supposed to go back to ChatGPT to finish creating the MCP server connection. To work around it for now, you'll need to set a password from your TRIGGERcmd profile page and login with your email/password instead. Give me a couple days to fix it.

At this point it requires a paid ("plus") version of ChatGPT. If you have a free account, it creates the connection but doesn't list it until you upgrade to a paid subscription. I hope they'll allow free accounts to use MCP servers too soon. I'm watching this thread for a resolution: https://community.openai.com/t/not-able-to-add-chatgpt-app-mcp-server-to-chatgpt/1365324/7

To add the TRIGGERcmd MCP server to your ChatGPT account:

Make sure you're logged into your TRIGGERcmd account.

Enable development mode here: https://chatgpt.com/#settings/Connectors/Advanced
8704bf08-29d3-4e8b-9382-599dd8e2f552-image.png

Go here: https://chatgpt.com/#settings/Connectors
237586cd-f0c4-4b06-9744-6cfeedef3867-image.png

Click "Create app" and set it up like this:
3e7fb33a-8fa4-4630-9943-15b13e7bf137-image.png

I paid for the ChatGPT plus upgrade and tested it:

121d4d94-e7af-4eda-966a-7d8e1af29114-image.png

@mega_big, on a Raspberry Pi, assuming you installed the agent using these instructions, your commands are in this file:

/root/.TRIGGERcmdData/commands.json

You'll see the default commands in there.

You can run these commands to edit it:

sudo su - cd /root/.TRIGGERcmdData nano commands.json

While the agent is running, it will detect changes in that commands.json file and create/remove triggers for those commands in your TRIGGERcmd account. If you mess up the json at all (an extra comma even), the agent will restore the last backup it took. You'll see that in your debug.log.

If you don't want to deal with editing text, you could create a command on your Windows PC using the "GUI Command Editor" then copy/paste the json text of that command from the "Text Command Editor" into your commands.json file.

@JoshuaJSlone, that's a known issue with the windows timeout command. It doesn't work in contexts that don't have an interactive terminal, like when running it via TRIGGERcmd. Here's one method that does work:

start /wait timeout 3

I've also added delays with the ping command like this:

ping 127.0.0.1 -n 2

@jett, you'll need to cancel your subscription from your Paypal account.

@Russ because I never clicked that and had no idea what it does. 😆

It worked. Now it shows the full name of the PC and the indicator is black.

I appreciate the help Russ. Have a good weekend and a happy Thanksgiving.