TRIGGERcmd
Runs commands on your computers remotely.
triggercmd-mcp-stdio
Local stdio MCP server for TRIGGERcmd

Features
This MCP server provides both general command management tools and dynamic command-specific tools:
Base Tools
list_commands- List all available TRIGGERcmd commands across your computersrun_command- Run any specific command by computer and command name
Dynamic Command Tools
The server automatically creates individual MCP tools for each of your TRIGGERcmd commands that have an mcpToolDescription field set. These tools:
- Are named using the pattern
run_{computer}_{command}(sanitized for MCP compatibility) - Use the
mcpToolDescriptionas the tool description for better AI understanding - Accept optional parameters if the command supports them
- Provide a more intuitive interface than the generic
run_commandtool
For example, if you have a command named "lights" on computer "office" with mcpToolDescription set to "Control the office lights - accepts colors (red, blue, green, white) or on/off", the server will automatically create a tool named run_office_lights with that description.
Setting mcpToolDescription
To enable dynamic tools for your commands:
- Log into your TRIGGERcmd account
- Edit the commands you want to expose as individual MCP tools
- Set the
mcpToolDescriptionfield with a clear description of what the command does and how to use parameters - Restart the MCP server to pick up the changes
Authentication
If the TRIGGERCMD_TOKEN environment variable is set, it will use that, otherwise it will try to read the token from your ~/.TRIGGERcmdData/token.tkn file in your user's home directory.
AI prompt examples
Use the #triggercmd mcp server to run notepad on laptop with parameter newnote.
You can also tell the LLM what the command does, and how the parameters work before you run your command. For example:
Prompt 1: The parameter of the "lights" command on the "office" computer in the #triggercmd mcp server is used to specify what color (red, white, green, or blue) to make the lights in my office. It also accepts on or off to turn the lights on or off.
Prompt 2: Turn the lights in my office green.
Prompt 3: Turn the lights in my office off.
Usage
Option 1: Direct Binary
If using Claude Desktop, add an entry like this to your claude_desktop_config.json file:
{
"mcpServers": {
"triggercmd": {
"command": "C:\\Users\\johndoe\\Downloads\\triggercmd-mcp-windows-amd64.exe"
}
}
}
If using VS Code, add an entry like this to your mcp.json file:
{
"servers": {
"triggercmd": {
"type": "stdio",
"command": "C:\\Users\\johndoe\\Downloads\\triggercmd-mcp-windows-amd64.exe"
}
}
}
Option 2: Docker Container
The server is also available as a Docker container. See the docker/README.md for detailed setup instructions.
Claude Desktop with Docker and mounted token file:
{
"mcpServers": {
"triggercmd": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/home/your_user/.TRIGGERcmdData/token.tkn:/home/triggercmd/.TRIGGERcmdData/token.tkn:ro",
"triggercmd-mcp:latest"
]
}
}
}
VS Code with Docker and Environment Variable:
{
"servers": {
"triggercmd": {
"type": "stdio",
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "TRIGGERCMD_TOKEN=your-token-here",
"triggercmd-mcp:latest"
]
}
}
}
Downloads
Mac:
Linux:
Windows:
NOTE: On Mac and Linux, you'll need to make the binary executable with a command like this:
chmod +x triggercmd-mcp-darwin-arm64
Demo
관련 서버
JIRA
Integrate with JIRA to allow AI assistants to directly interact with JIRA issues.
GistPad MCP
Manage and share personal knowledge, daily notes, and reusable prompts using GitHub Gists.
Brainstorm
Multi-round AI debates between GPT, DeepSeek, Groq, and Claude — all models argue, critique, and synthesize inside your coding assistant.
Todoist MCP
Interact with your Todoist account to manage tasks and projects.
mindpad
Save encrypted notes to your mindpad account
Bitly MCP Server
Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.
Google Sheets
A server for comprehensive Google Sheets integration, requiring Google OAuth credentials.
physbound
PhysBound is a specialized "Physics Linter" for AI that deterministically validates RF and thermodynamic claims against hard physical limits, preventing hallucinations in engineering workflows.
Canvas MCP Server
An MCP server for interacting with the Canvas LMS API.
Joplin MCP Server
A server that enables access to Joplin notes and to-dos through the Model Context Protocol (MCP).
