Install the Corla adapter, log in with your grant, and start receiving enterprise context in your AI dev tools — in under 5 minutes.
Install the adapter globally using npm:
This gives you the corla CLI command. Verify the installation:
Run the login command with your credentials:
You'll be prompted for:
https://broker.corla.ai (or the URL your admin provided)acme-engineeringOn success, you'll receive a token. The CLI will show you how to set it:
Add this to your shell profile (~/.zshrc or ~/.bashrc) so it persists across terminal sessions.
Navigate to your project directory and run:
This creates an .mcp.json file in your project root that configures Corla as an MCP server:
If you use VS Code, it also creates .vscode/mcp.json for VS Code Copilot integration.
That's it. Your AI tools will now automatically load enterprise context when working in this project. The context is fetched from the broker, compiled and scoped to your role, and delivered to your AI tool.
Context loads automatically via MCP
Reads .mcp.json for context
Uses .vscode/mcp.json
To verify the connection is working:
You should see your enterprise name, project, role, and token expiry.
When your AI tool starts a session, it connects to the Corla broker via MCP and:
You never see the raw assets. Your AI tool receives processed context that helps it write better, more aligned code — without exposing the enterprise's proprietary material.
corla login again to get a new one. Update CORLA_TOKEN in your shell profile.
CORLA_TOKEN is set in your environment and .mcp.json exists in your project root. Restart your AI tool after adding the config.
If you run into any issues, reach out to your enterprise admin or contact us at info@noitechnologies.com.