> ## Documentation Index
> Fetch the complete documentation index at: https://docs.brivvy.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini

> Connect Brivvy to Gemini CLI so the model can access brand voice rules and generate on-brand content directly from the terminal.

Gemini CLI supports remote MCP servers via HTTP, which means you can connect Brivvy's MCP server with a single configuration entry. Once connected, Gemini can call Brivvy tools mid-conversation to retrieve brand voice guidelines and list templates without leaving the terminal.

## Before you start

* Gemini CLI installed (run `npm install -g @google/gemini-cli` if not already).
* A Brivvy account on a plan that includes MCP access.
* A text editor for modifying `settings.json`.

## Steps

1. Open a terminal and navigate to the Gemini CLI config directory. The path depends on your platform:

   | Platform      | Path                             |
   | ------------- | -------------------------------- |
   | macOS / Linux | `~/.gemini/settings.json`        |
   | Windows       | `%APPDATA%\gemini\settings.json` |

   Create the file if it does not exist.

2. Open `settings.json` in a text editor. The file uses standard JSON format. If the file is empty, start with an opening and closing curly brace `{}` as the base structure.

3. Paste the following configuration inside the top-level object. If a `mcpServers` block already exists, add `"brivvy"` as an additional entry rather than creating a second block.

   ```json theme={null}
   {
     "mcpServers": {
       "brivvy": {
         "httpUrl": "https://mcp.brivvy.io",
         "oauth": {
           "enabled": true
         }
       }
     }
   }
   ```

4. Save the file. Make sure the JSON is valid before closing the editor. A trailing comma after the last entry or mismatched brackets are common issues that will prevent Gemini CLI from starting.

5. Run `gemini` in the terminal. The CLI reads `settings.json` on startup and attempts to connect to each configured MCP server.

6. Inside the Gemini CLI session, run `/mcp auth brivvy` to start the OAuth flow. Your browser will open an authorization page where you can sign in to Brivvy and grant access.

7. After authentication completes, type `/mcp` and press <kbd>Enter</kbd>. The output lists all connected servers and their available tools. `brivvy` should appear with tools such as `get_voice` and `list_templates`.

8. Send a prompt that requires brand voice context, for example: "Using Brivvy, get the brand voice rules and write a two-sentence product update." Gemini CLI will call the appropriate Brivvy tool and incorporate the returned guidelines into the response.

## How to know it worked

The `/mcp` command shows `brivvy` with a connected status and a list of tools. A test prompt that references Brivvy returns a response shaped by the brand voice rules rather than a generic output.