Connecting Your Personal VerbAI MCP to Gemini CLI

This guide explains how to connect your personal VerbAI MCP (Model Context Protocol) server to the Gemini CLI, allowing you to pull, analyze, and work with your own behavioral data directly from your terminal.

Gemini offers a large context window and excellent support for MCP integrations, making it a powerful tool for developers and technical users who want unrestricted access to their VerbAI data.

Overview

VerbAI exposes your personal data through an MCP server. While Claude supports MCP natively, the Gemini CLI is an excellent alternative for users who prefer command‑line workflows or need larger context limits.

Using Gemini CLI with your VerbAI MCP lets you:

• Pull large amounts of behavioral data

• Run custom queries

• Process data programmatically

• Use the MCP tools without hitting strict context limits

You can also integrate your personal MCP into n8n for building pipelines, automations, and visual reports.

1

Install the Gemini CLI

Download and install the Gemini CLI here:

https://geminicli.com/

After installation, you can use the command gemini in your terminal.

2

Add Your VerbAI MCP Server

Run the following command in your terminal to register your MCP server with Gemini:

gemini mcp add --transport http verbai 
https://api.generationlab.org/mcp
--header "Authorization: Bearer YOUR_MCP_API_KEY"

Replace YOUR_MCP_API_KEY with the API key you created in your VerbAI dashboard.

⚠️ Important: Do not share this token with anyone. It grants full access to your personal data.

If the command runs successfully, your MCP server is now registered.

3

Verify MCP Connection

Check that Gemini recognizes the MCP server by running:

gemini mcp list

You should see your VerbAI MCP listed with a green checkmark and a status of Connected.

4

Start Interacting With Your VerbAI MCP

To begin interacting with Gemini, run:

gemini

This launches the Gemini CLI in interactive mode.

You can now query your VerbAI MCP. For example:

Using verbai MCP, pull search behavioral data about searches done in the past 24 hours

Make sure you explicitly instruct Gemini to use the VerbAI MCP at the beginning of your prompt—otherwise, it may respond without querying your data.

5

Approve MCP Tool Execution

During your first attempts, Gemini will ask you whether it is allowed to run MCP tools.

Use your arrow keys to select:

"Yes, always allow..."

Confirm with Enter.

This approval is required only once.