Get ad performance metrics through simple chat. For founders using Claude AI or similar.
intermediate⏱ 30 minutes💵 Free + LLM API costs
650 stars148 forksPythonQuality 9/10Updated 10/16/2025100% free · open source
What it is
Connects Google Ads with AI tools for data analysis through natural language conversations.
What you can make with it
Automations that fetch and analyze Google Ads campaign information and performance metrics via chat with Claude or Cursor.
How it helps
Saves time by letting you discuss advertising data with AI, and easily access key metrics and ad management tools without manually logging in.
Real use case example
"A founder who spends hours analyzing Google Ads data could use this to ask Claude to show their ad campaign performance, and then discuss any insights they find to optimize their ads."
If you're new
This is a good starting point for beginners who want to work with Google Ads and AI tools together.
If you're senior
Senior engineers and professionals will appreciate this integration for automating Google Ads data analysis and ad management tasks.
Common confusion cleared up
You can use it immediately after setting up Claude or Cursor with your Google Ads account.
Best inside these AI tools
Claude DesktopCursorCodex CLI
Pairs with
CLAUDE APICursorWindsurf
Why we list it on WorkflowStacks: This marketplace includes it because it integrates a popular ad platform with powerful AI tools for data exploration.
What it does
Get ad performance metrics and manage your Google Ads campaigns through natural language conversations with Claude AI or similar tools.
Install / run
Clone the repository from https://github.com/cohnen/mcp-google-ads and follow the setup instructions in the README.
When to use it
•You want to track the performance of your Google Ads campaigns without leaving your chat interface.
•You need to analyze keyword analytics and make data-driven decisions for your ad strategy.
•You want to manage your ad campaigns, including creating and editing ads, through a conversational interface.
Quick start
1Create a Google Ads API credentials file by following the instructions in the README.
2Configure your Claude AI or similar tool to connect to the mcp-google-ads server.
3Start the mcp-google-ads server using a command similar to 'python -m mcp_google_ads.server' (refer to the README for exact command).
4Test the integration by sending a simple query to your chat interface, such as 'What is my current ad spend?'
5Explore the available commands and features by checking the README or the chat interface's help menu.
Ready-to-paste prompt
What are my top-performing ad groups for the last 30 days, and what is their average cost-per-conversion?
Heads up: Make sure you have a Google Ads API key and a Google Cloud Platform project set up before attempting to use the mcp-google-ads tool, as it requires these credentials to function correctly.
Saves to your device
Topics
ai
claude
google-ads
mcp
mcp-server
What's inside — free to inspect
No purchase needed
Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.
15
top-level files
3
folders
172K
repo size
MIT
license
Key files
README.md
requirements.txt
File tree
.cursor/
docs/
pulls/
.env.example
.gitignore
.python-version
bg.jpeg
format_customer_id_test.py
gaql-google-ads-query-language.mdc
google_ads_server.py
google-ads.svg
ixigo-logo.png
LICENSE
pyproject.toml
README.md
requirements.txt
test_google_ads_mcp.py
test_token_refresh.py
Quick Actions
Details
Creator
cohnen
Language
Python
Category
mcp-server
Published
3/20/2025
Are you the creator of this tool? Claim your listing → and earn 85% of every sale.
Related skills
More mcp-server tools founders pair with this one.