Step 1: Start with the Agent Skills¶

Install and authenticate the CLI, then give your coding agent the Omnistrate skills. The skills use the CLI by default; MCP is optional. The web console remains available for configuration and inspection.

Install and Authenticate the CLI¶

You need an Omnistrate account to authenticate the CLI. If necessary, sign up and complete email verification. Confirm that you sign in to the intended organization.

Omnistrate CTL lets you build products, manage plans, and operate deployments. Follow the CLI installation instructions, then verify the installation and sign in:

omnistrate-ctl --help
omnistrate-ctl login

Choose email/password or SSO as appropriate. See the login methods and CLI command reference for details.

Install the Agent Skills¶

Use a coding agent that can run shell commands. From your project directory, run the skills installer and select the agents and skills you want:

npx skills add omnistrate-oss/agent-instructions

The installer requires Node.js/npm with npx available. Follow the agent skills repository for agent-specific installation options. Alternatively, CTL can initialize the agent instructions in your project:

omnistrate-ctl agent init

Give your agent a concrete starting request¶

Use the Omnistrate FDE onboarding skill. My product uses [artifact paths and versions].
Customers need [Hosted, BYOC account or VPC, existing Kubernetes, or air-gapped installation].
Ask for missing requirements, propose the plan structure, and build one minimal development
deployment. Reuse our existing assets. Validate the spec, test the application, and document
the result. Ask before creating billable resources, changing permissions, or deleting anything.

Review the agent's proposed deployment model, environment, account boundary, and resource changes before execution. Never provide credentials in a prompt or commit them to Git.

Optional MCP Integration¶

Connect your AI tools to Omnistrate using the Model Context Protocol (MCP), an open standard that lets AI assistants interact with your Omnistrate services and infrastructure.

What is Omnistrate MCP?¶

Omnistrate MCP is Omnistrate's official MCP server. It is a local MCP server that gives AI tools secure access to your Omnistrate projects and resources through the omnistrate-ctl command-line interface.

It integrates with popular AI assistants like Claude, enabling you to:

• Search and navigate Omnistrate documentation and knowledge base
• Manage services, environments, and service plans
• Create and manage instances and deployments
• Monitor service health and operational events
• Manage subscriptions and customer access
• Configure deployment cells and cloud accounts
• Analyze costs and audit logs

Connecting to Omnistrate MCP¶

To use Omnistrate MCP, you need to have omnistrate-ctl installed and configured on your system. The MCP server communicates with Omnistrate through your local CLI installation.

Prerequisites¶

• omnistrate-ctl CLI tool installed and in your PATH
• Omnistrate account with appropriate permissions
• Authentication configured for your Omnistrate account

Supported clients¶

Omnistrate MCP can be integrated with various AI tools and IDEs that support the Model Context Protocol:

• Claude Code
• Claude.ai and Claude for Desktop
• Cursor
• VS Code with Copilot
• Cline
• Windsurf
• Gemini Code Assist
• Gemini CLI

Setup the MCP Server¶

Connect your AI client to Omnistrate MCP and authorize access to manage your Omnistrate infrastructure.

Claude Code¶

# Install Claude Code
npm install -g @anthropic-ai/claude-code

# Configure Omnistrate MCP Server
claude mcp add --scope user omnistrate omctl mcp start

# Start coding with Claude
claude

Claude.ai and Claude for Desktop¶

Custom connectors using remote MCP are available on Claude and Claude Desktop for users on Pro, Max, Team, and Enterprise plans.

1. Open Settings in the sidebar
2. Navigate to Connectors and select Add custom connector
3. Configure the connector:
4. Name: Omnistrate
5. Command: omnistrate-ctl mcp start

Cursor¶

Add the snippet below to your project-specific or global .cursor/mcp.json file:

{
  "mcpServers": {
    "omnistrate": {
      "command": "omnistrate-ctl",
      "args": ["mcp", "start"]
    }
  }
}

Once the server is added, Cursor will attempt to connect. Ensure your Omnistrate credentials are configured.

VS Code with Copilot¶

Installation¶

Enable the mcp server with one command:

omnistrate-ctl mcp vscode enable

or manually:

1. Open the Command Palette (Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS)
2. Run MCP: Add Server
3. Select Stdio
4. Enter the following details:
5. Command: omnistrate-ctl
6. Arguments: mcp start
7. Name: Omnistrate
8. Select Global or Workspace depending on your needs
9. Click Add

Authorization¶

Now that you've added Omnistrate MCP, let's start the server:

1. Open the Command Palette (Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS)
2. Run MCP: List Servers
3. Select Omnistrate
4. Click Start Server
5. Ensure your Omnistrate credentials are configured in your environment

Cline¶

Add Omnistrate MCP to your Cline configuration:

1. Open Cline settings
2. Add a new MCP server:
3. Name: Omnistrate
4. Command: omnistrate-ctl
5. Arguments: mcp start
6. Save and restart Cline

Windsurf¶

Add the snippet below to your mcp_config.json file:

{
  "mcpServers": {
    "omnistrate": {
      "command": "omnistrate-ctl",
      "args": ["mcp", "start"]
    }
  }
}

Gemini Code Assist¶

To set up Omnistrate MCP with Gemini Code Assist:

1. Ensure you have Gemini Code Assist installed in your IDE
2. Add the following configuration to your ~/.gemini/settings.json file:

{
  "mcpServers": {
    "omnistrate": {
      "command": "omnistrate-ctl",
      "args": ["mcp", "start"]
    }
  }
}

1. Restart your IDE to apply the configuration
2. Ensure your Omnistrate credentials are configured

Gemini CLI¶

Gemini CLI shares the same configuration as Gemini Code Assist. To set up Omnistrate MCP with Gemini CLI:

1. Ensure you have the Gemini CLI installed
2. Add the following configuration to your ~/.gemini/settings.json file:

{
  "mcpServers": {
    "omnistrate": {
      "command": "omnistrate-ctl",
      "args": ["mcp", "start"]
    }
  }
}

1. Run the Gemini CLI and use the /mcp list command to see available MCP servers
2. Ensure your Omnistrate credentials are configured

Setup steps may vary based on your MCP client version. Always check your client's documentation for the latest instructions.

Agent Skills and MCP¶

The skills installed above use omnistrate-ctl by default. Enable MCP only when you want your agent to call Omnistrate tools through an MCP connection; it is not a prerequisite for CLI-based onboarding.

Security best practices¶

The MCP ecosystem and technology are evolving quickly. Here are our current best practices to help you keep your workspace secure:

Verify your setup¶

• Ensure omnistrate-ctl is installed from the official Omnistrate repository
• Verify that your Omnistrate credentials are properly configured

Trust and verification¶

• Connecting to Omnistrate MCP grants the AI system you're using the same access as your Omnistrate user account
• Review the permissions and access levels of each AI tool you connect

Enable human confirmation¶

• Always enable human confirmation in your workflows to maintain control and prevent unauthorized changes
• Prevents accidental or harmful changes to your services and deployments

Contributing¶

We welcome contributions to improve the Omnistrate agent instructions! If you have suggestions for better workflows, additional skills, or improvements to existing guidance, please visit the agent-instructions repository and submit a pull request or open an issue.

Next: Step 2.1: Select the deployment model, then Step 2.2: Cloud account onboarding.