Welcome to the Gemini CLI integration guide. This guide will help you connect ByteRover with Gemini CLI, providing Google’s AI with persistent memory of your coding patterns and solutions.

​
What You’ll Need

  • Gemini CLI installed and configured
  • A ByteRover account

​
Getting Started

​
1. Start the Connection

Go to your ByteRover dashboard and:
  1. Find the “Connect your agent” section
  2. Click on Gemini CLI from the list
  3. Hit the “Connect with Gemini CLI” button

​
2. Connect ByteRover to Gemini CLI

Step 1: Open your Gemini settings file: 
~/.gemini/settings.json
Step 2: Add the following MCP server block: 
{
  "mcpServers": {
    "byterover-mcp": {
      "httpUrl": "https://mcp.byterover.dev/v2/mcp",
      "headers": {
        "Authorization": "Bearer [DASHBOARD_TOKEN]"
      }
    }
  }
}
Step 3: Reload Gemini CLI to apply changes. Run /mcp to confirm your connection. You should see byterover-mcp listed with available tools.

​
Test It

Try storing a pattern: 
Store this async retry utility to ByteRover:

async function retry(fn, maxAttempts = 3, delay = 1000) {
  for (let attempt = 1; attempt <= maxAttempts; attempt++) {
    try {
      return await fn();
    } catch (error) {
      if (attempt === maxAttempts) {
        throw error;
      }
      await new Promise(resolve => setTimeout(resolve, delay * attempt));
    }
  }
}
Gemini should confirm successful storage.

​
Benefits

​
Troubleshooting

Join our Discord community for Gemini CLI tips and support.