Gemini Cli Googleadsagent

Gemini CLI + Google Ads Agent

> Open-source Google Ads management commands and AI agent skills for > Gemini CLI. Analyze campaign > performance, audit accounts, optimize PPC spend, and generate GAQL queries — > all from your terminal.

[](https://github.com/google-gemini/gemini-cli/blob/main/LICENSE) [](https://www.npmjs.com/package/@google/gemini-cli) [](https://github.com/itallstartedwithaidea/gemini-cli-googleadsagent/wiki) [](https://github.com/itallstartedwithaidea/advertising-hub) [](https://ahmeego.com)

Part of the Advertising Hub ecosystem — 14 ad platform APIs, 25+ AI agents, MCP servers | ahmeego.com | MiniAgent

Keywords: Google Ads API, Google Ads automation, PPC management, campaign analysis, GAQL queries, account audit, bid optimization, ad creative testing, Performance Max, Google Ads scripts, AI advertising agent, Gemini CLI extensions, digital marketing AI, paid media tools

---

Companion Extension — google-ads-gemini-extension v2.4.1

For live Google Ads API access (MCP server, 26 tools including write operations), pair this CLI fork with the google-ads-gemini-extension:

gemini extensions install https://github.com/itallstartedwithaidea/google-ads-gemini-extension

v2.4.1 ships zero-setup sign-in. After installing, run /google-ads:login — your browser opens to ahmeego.com, you pick any Google account with Google Ads access, approve, and you're signed in. No Cloud Console setup, no client IDs, no secrets ever touch the CLI. The Google refresh token stays encrypted on the site; only an opaque session id is stored locally (OS keychain when available). Multiple identities supported with /google-ads:status, /google-ads:switch , /google-ads:logout.

Full details in the extension README and CHANGELOG.

Troubleshooting sign-in

| Symptom | Fix | | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Error 400: redirect_uri_mismatch with http://127.0.0.1:/callback | Your Gemini session started before v2.4 landed on disk. Run /quit, then gemini again — the MCP server reloads with the proxy flow. | | Sign-in timed out after 120s | Browser didn't open or you didn't complete consent in time. Re-run /google-ads:login — the CLI also prints the URL you can paste manually. | | Access blocked: This app's request is invalid with a ahmeego.com redirect | Your Google account isn't on the OAuth consent screen's "Test users" list for this project. Ask the project owner to add you, or use a pre-approved account. |

---

Google Ads Commands (this repo)

This fork extends Gemini CLI with three Google Ads slash commands and a domain-specific agent skill. These are prompt-only — they provide expert framing for the model but do not make live API calls on their own. For live API access install the companion extension above.

/google-ads-analyze — Campaign Performance Analysis

/google-ads-analyze Show me top spending campaigns last 30 days with declining ROAS

• Suggests relevant GAQL queries to pull the data
• Presents findings in clear tables
• Identifies anomalies and opportunities
• Recommends specific, actionable next steps

/google-ads-audit — Comprehensive Account Audit

/google-ads-audit Full audit of the Hopeworks nonprofit account

Covers 7 audit areas with severity ratings (Critical / High / Medium / Low):

• Account structure, bidding strategy, budget allocation
• Keyword health, ad creative, targeting, conversion tracking

/google-ads-optimize — Optimization Recommendations

/google-ads-optimize We need to reduce CPA by 15% without losing volume

• Identifies top 3-5 highest-impact optimization opportunities
• Prioritizes by effort vs. impact with risk levels
• Covers wasted spend, bid efficiency, creative fatigue, and targeting gaps

Google Ads Agent Skill

The included skill (.gemini/skills/google-ads-agent/) activates automatically for any advertising-related question. It provides:

• GAQL expertise — knows Google Ads Query Language syntax, common patterns,

and cost micro conversion

• API v22 knowledge — current API version, auth patterns, rate limits
• Campaign analysis — trends, anomalies, underperformers, budget allocation
• Write safety — always presents proposed changes before execution

Quick Start

# Clone this repo
git clone https://github.com/itallstartedwithaidea/gemini-cli-googleadsagent.git
cd gemini-cli-googleadsagent

# Install and build
npm install
npm run build

# Run (will prompt for Google sign-in on first use)
npm start

Or use the commands/skills in any project by copying the .gemini/ directory:

# Copy Google Ads commands + skills to your own project
cp -r gemini-cli-googleadsagent/.gemini/commands/google-ads-*.toml your-project/.gemini/commands/
cp -r gemini-cli-googleadsagent/.gemini/skills/google-ads-agent/ your-project/.gemini/skills/

Related Projects

| Project | Description | | ----------------------------------------------------------------------------------------------------- | -------------------------------------------------------------- | | advertising-hub | One-stop shop for 14 ad platform APIs, MCP servers, and agents | | google-ads-api-agent | Enterprise Google Ads agent — 28 API actions, live read/write | | google-ads-mcp | MCP server for Google Ads API access | | google-ads-skills | Claude Code / Codex / Gemini CLI skills for Google Ads | | MiniAgent | Trainable 26M-param advertising AI + 14 MCP servers | | google-ads-claudecodeskill | Claude Code skill for Google Ads management |

---

Documentation

Full documentation is available on the Wiki:

• Getting Started

— Installation, authentication, first run

• Commands Reference

— Full docs for all three commands with examples

• Google Ads Agent Skill

— GAQL patterns, API v22 knowledge, write safety

• Configuration

— Settings, env variables, model selection

• Related Projects

— Full ecosystem overview

---

About Gemini CLI (Upstream)

This is a fork of google-gemini/gemini-cli with Google Ads-specific extensions.

Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model.

Learn all about Gemini CLI in the official documentation.

🚀 Why Gemini CLI?

• 🎯 Free tier: 60 requests/min and 1,000 requests/day with personal Google

account.

• 🧠 Powerful Gemini 3 models: Access to improved reasoning and 1M token

context window.

• 🔧 Built-in tools: Google Search grounding, file operations, shell

commands, web fetching.

• 🔌 Extensible: MCP (Model Context Protocol) support for custom

integrations.

• 💻 Terminal-first: Designed for developers who live in the command line.
• 🛡️ Open source: Apache 2.0 licensed.

📦 Installation

See [Gemini CLI installation, execution, and releases](./docs/get-started/installation.md) for recommended system specifications and a detailed installation guide.

Quick Install

Run instantly with npx

# Using npx (no installation required)
npx @google/gemini-cli

Install globally with npm

npm install -g @google/gemini-cli

Install globally with Homebrew (macOS/Linux)

brew install gemini-cli

Install globally with MacPorts (macOS)

sudo port install gemini-cli

Install with Anaconda (for restricted environments)

# Create and activate a new environment
conda create -y -n gemini_env -c conda-forge nodejs
conda activate gemini_env

# Install Gemini CLI globally via npm (inside the environment)
npm install -g @google/gemini-cli

Release Cadence and Tags

See [Releases](./docs/releases.md) for more details.

Preview

New preview releases will be published each week at UTC 23:59 on Tuesdays. These releases will not have been fully vetted and may contain regressions or other outstanding issues. Please help us test and install with preview tag.

npm install -g @google/gemini-cli@preview

Stable

• New stable releases will be published each week at UTC 20:00 on Tuesdays, this

will be the full promotion of last week's preview release + any bug fixes and validations. Use latest tag.

npm install -g @google/gemini-cli@latest

Nightly

• New releases will be published each day at UTC 00:00. This will be all changes

from the main branch as represented at time of release. It should be assumed there are pending validations and issues. Use nightly tag.

npm install -g @google/gemini-cli@nightly

📋 Key Features

Code Understanding & Generation

• Query and edit large codebases
• Generate new apps from PDFs, images, or sketches using multimodal capabilities
• Debug issues and troubleshoot with natural language

Automation & Integration

• Automate operational tasks like querying pull requests or handling complex

rebases

• Use MCP servers to connect new capabilities, including

media generation with Imagen, Veo or Lyria

• Run non-interactively in scripts for workflow automation

Advanced Capabilities

• Ground your queries with built-in

Google Search for real-time information

• Conversation checkpointing to save and resume complex sessions
• Custom context files (GEMINI.md) to tailor behavior for your projects

GitHub Integration

Integrate Gemini CLI directly into your GitHub workflows with Gemini CLI GitHub Action:

• Pull Request Reviews: Automated code review with contextual feedback and

suggestions

• Issue Triage: Automated labeling and prioritization of GitHub issues based

on content analysis

• On-demand Assistance: Mention @gemini-cli in issues and pull requests

for help with debugging, explanations, or task delegation

• Custom Workflows: Build automated, scheduled and on-demand workflows

tailored to your team's needs

🔐 Authentication Options

Choose the authentication method that best fits your needs:

Option 1: Login with Google (OAuth login using your Google Account)

✨ Best for: Individual developers as well as anyone who has a Gemini Code Assist License. (see quota limits and terms of service for details)

Benefits:

• Free tier: 60 requests/min and 1,000 requests/day
• Gemini 3 models with 1M token context window
• No API key management - just sign in with your Google account
• Automatic updates to latest models

Start Gemini CLI, then choose Login with Google and follow the browser authentication flow when prompted

gemini

If you are using a paid Code Assist License from your organization, remember to set the Google Cloud Project

# Set your Google Cloud Project
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
gemini

Option 2: Gemini API Key

✨ Best for: Developers who need specific model control or paid tier access

Benefits:

• Free tier: 1000 requests/day with Gemini 3 (mix of flash and pro)
• Model selection: Choose specific Gemini models
• Usage-based billing: Upgrade for higher limits when needed

# Get your key from https://aistudio.google.com/apikey
export GEMINI_API_KEY="YOUR_API_KEY"
gemini

Option 3: Vertex AI

✨ Best for: Enterprise teams and production workloads

Benefits:

• Enterprise features: Advanced security and compliance
• Scalable: Higher rate limits with billing account
• Integration: Works with existing Google Cloud infrastructure

# Get your key from Google Cloud Console
export GOOGLE_API_KEY="YOUR_API_KEY"
export GOOGLE_GENAI_USE_VERTEXAI=true
gemini

For Google Workspace accounts and other authentication methods, see the [authentication guide](./docs/get-started/authentication.md).

🚀 Getting Started

Basic Usage

Start in current directory

gemini

Include multiple directories

gemini --include-directories ../lib,../docs

Use specific model

gemini -m gemini-2.5-flash

Non-interactive mode for scripts

Get a simple text response:

gemini -p "Explain the architecture of this codebase"

For more advanced scripting, including how to parse JSON and handle errors, use the --output-format json flag to get structured output:

gemini -p "Explain the architecture of this codebase" --output-format json

For real-time event streaming (useful for monitoring long-running operations), use --output-format stream-json to get newline-delimited JSON events:

gemini -p "Run tests and deploy" --output-format stream-json

Quick Examples

Start a new project

cd new-project/
gemini
> Write me a Discord bot that answers questions using a FAQ.md file I will provide

Analyze existing code

git clone https://github.com/google-gemini/gemini-cli
cd gemini-cli
gemini
> Give me a summary of all of the changes that went in yesterday

📚 Documentation

Getting Started

• [Quickstart Guide](./docs/get-started/index.md) - Get up and running

quickly.

• [Authentication Setup](./docs/get-started/authentication.md) - Detailed

auth configuration.

• [Configuration Guide](./docs/reference/configuration.md) - Settings and

customization.

• [Keyboard Shortcuts](./docs/reference/keyboard-shortcuts.md) -

Productivity tips.

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: itallstartedwithaidea
• Source: itallstartedwithaidea/gemini-cli-googleadsagent
• License: Apache-2.0
• Homepage: https://googleadsagent.ai

Install and usage instructions live in the source repository linked above.