Installation
This guide will help you set up TRMX AI and the Model Context Protocol (MCP) in your development environment.
System Requirements
Before you begin, make sure your system meets these requirements:
| Requirement | Minimum | Recommended |
|---|---|---|
| Node.js | 16.0.0 | 18.0.0 or newer |
| NPM/Yarn | 7.0.0 / 1.22.0 | 9.0.0 / 3.0.0 |
| Memory | 4GB RAM | 8GB RAM |
| OS | macOS 10.15+, Windows 10+, Ubuntu 20.04+ | Latest versions |
Installation Options
There are several ways to install and use TRMX AI:
CLI Installation
Install the TRMX CLI to create and manage MCP projects
Learn more →SDK Installation
Add TRMX SDKs to your existing projects
Learn more →Docker Setup
Use pre-configured Docker images for development
Learn more →Installing the TRMX CLI
The TRMX Command Line Interface (CLI) is the primary tool for creating, developing, and deploying MCP applications.
# Using npm (recommended)
npm install -g @trmx/cli
# Using yarn
yarn global add @trmx/cli
# Verify installation
trmx --version
Setting Up Your Environment
1. Create a TRMX AI Account
You'll need a TRMX AI account to access the platform services:
- Sign up at trmx.ai/signup
- Verify your email address
- Log in to the TRMX AI Dashboard
2. Get Your API Key
- Navigate to the API Keys section in your dashboard
- Create a new API key
- Copy the key to a secure location (it will only be shown once)
3. Configure the CLI
Log in to your TRMX AI account through the CLI:
# Log in using the CLI
trmx login
# Follow the prompts to enter your API key
SDK Installation
Depending on your programming language, install the appropriate SDK:
# Create a new project directory
mkdir my-mcp-project
cd my-mcp-project
# Initialize the project
npm init -y
# Install the SDK
npm install @trmx/client @trmx/server
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the SDK
pip install trmx-client trmx-server
<!-- In your pom.xml -->
<dependencies>
<dependency>
<groupId>com.trmx</groupId>
<artifactId>trmx-client</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>com.trmx</groupId>
<artifactId>trmx-server</artifactId>
<version>1.0.0</version>
</dependency>
</dependencies>
# Using .NET CLI
dotnet add package Trmx.Client
dotnet add package Trmx.Server
# Install the Go SDK
go get github.com/trmx/client-go
go get github.com/trmx/server-go
Docker Installation
For containerized environments, we provide Docker images:
# Pull the TRMX AI development image
docker pull trmxai/trmx-dev:latest
# Run a container with the image
docker run -it -p 3000:3000 -v $(pwd):/app trmxai/trmx-dev:latest
Development Environment Setup
IDE Extensions
To enhance your development experience, we recommend these extensions:
Environment Variables
Create a .env file in your project root with these settings:
TRMX_API_KEY=your_api_key_here
TRMX_ENV=development
Verification
Verify your installation with this simple test:
# Create a test MCP server
trmx init test-server
# Navigate to the project
cd test-server
# Start the server
trmx dev
You should see a message confirming your MCP server is running on http://localhost:3000.
Troubleshooting
"Command not found: trmx"
Ensure the global npm/yarn bin directory is in your PATH environment variable. You can fix this by:
# For npm
export PATH="$PATH:$(npm config get prefix)/bin"
# For yarn
export PATH="$PATH:$(yarn global bin)"
Add this line to your shell profile (.bashrc, .zshrc, etc.) for permanent effect.
Authentication errors
Verify you're using the correct API key from your TRMX AI dashboard. Try re-running:
trmx login
And enter your API key again when prompted.
Connection issues
Check your internet connection and firewall settings. If behind a corporate firewall, you may need to configure proxy settings.
Next Steps
Now that you have TRMX AI installed, follow our Quick Start Guide to create your first MCP application.