Using Linkly AI in Gemini CLI

Prerequisites

Gemini CLI installed
Linkly AI Desktop running with the MCP service active

bash Install via npm npm install -g @google/gemini-cli  bash Install     via Homebrew (macOS) brew install google-gemini/gemini-cli/gemini-cli

Configuration Steps

MCP HTTP (Recommended)
MCP Stdio
Remote Access

Edit ~/.gemini/settings.json and add the following to mcpServers:

{
  "mcpServers": {
    "linkly-ai": {
      "httpUrl": "http://127.0.0.1:60606/mcp"
    }
  }
}

First install Linkly AI CLI.Edit ~/.gemini/settings.json and add the following to mcpServers:

{
  "mcpServers": {
    "linkly-ai": {
      "command": "linkly",
      "args": ["mcp"]
    }
  }
}

First complete remote access configuration, with the desktop tunnel showing● Connected.Edit ~/.gemini/settings.json:

{
  "mcpServers": {
    "linkly-ai": {
      "httpUrl": "https://mcp.linkly.ai/mcp",
      "headers": {
        "Authorization": "Bearer <your API Key>"
      }
    }
  }
}

The configuration file supports ${env:VAR_NAME} syntax to read environment variables, avoiding writing the API Key in plaintext:

"Authorization": "Bearer ${env:LINKLY_API_KEY}"

Getting Started

Once configured, launch Gemini CLI and ask questions directly:

gemini
> Search my documents for content about the project architecture

FAQ

Configuration file does not exist

Running gemini for the first time will automatically create the ~/.gemini/ directory. You can also create it manually: bash mkdir -p ~/.gemini && touch ~/.gemini/settings.json

Tools are not being called

Run the /mcp command in Gemini CLI to view the list of loaded MCP servers, and confirm that linkly-ai appears in the list.

AI Assistants

Coding AI Agents

AI Workflows

Other

Using Linkly AI in Gemini CLI

Prerequisites

Configuration Steps

Getting Started

FAQ

AI Assistants

Coding AI Agents

AI Workflows

Other

​Prerequisites

​Configuration Steps

​Getting Started

​FAQ

Prerequisites

Configuration Steps

Getting Started

FAQ