Google Ads MCP Server
MCP server that lets any LLM manage Google Ads campaigns from the terminal. Supports read and write operations.
README
Google Ads MCP Server
MCP server that lets any LLM (Claude, Cursor, etc.) manage Google Ads campaigns from the terminal. Supports read and write operations.
Quick Start
pip install google-ads-mcp
google-ads-mcp auth
The auth command walks you through getting credentials, opens your browser for Google sign-in, and saves everything to ~/.config/google-ads-mcp/credentials.json.
Then add to your .mcp.json:
{
"mcpServers": {
"google-ads": {
"command": "google-ads-mcp",
"args": ["serve"]
}
}
}
No environment variables needed — the server auto-loads saved credentials.
Alternative: uvx (no install)
{
"mcpServers": {
"google-ads": {
"command": "uvx",
"args": ["google-ads-mcp", "serve"]
}
}
}
Run uvx google-ads-mcp auth first to set up credentials.
Alternative: environment variables
If you prefer env vars over saved credentials:
{
"mcpServers": {
"google-ads": {
"command": "google-ads-mcp",
"args": ["serve"],
"env": {
"GOOGLE_ADS_DEVELOPER_TOKEN": "your-token",
"GOOGLE_ADS_CLIENT_ID": "your-client-id",
"GOOGLE_ADS_CLIENT_SECRET": "your-secret",
"GOOGLE_ADS_REFRESH_TOKEN": "your-refresh-token"
}
}
}
}
Env vars take priority over saved credentials when both are present.
Tools (10)
Read
list_accounts— List accessible customer accountslist_campaigns— List campaigns with status & budgetget_campaign_performance— Impressions, clicks, cost, conversions, CTR, CPC
Write
create_campaign— Create a search campaign (PAUSED by default)update_campaign_budget— Change daily budgetpause_campaign/enable_campaign— Toggle campaign statuscreate_ad_group— Create ad group in a campaignadd_keywords— Add keywords to an ad group (EXACT, PHRASE, BROAD)create_ad— Create responsive search ad
Development Setup
cd google_ads_mcp
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
Tests
pytest tests/ -v
All tests use mocked Google Ads client — no credentials needed.
Design decisions
- Dollar amounts in params (not micros) — LLMs think in dollars
- Campaigns created PAUSED by default — safety first
- All tools return JSON — structured output for LLMs
- Errors return JSON too (never raise) — actionable diagnostics
- Lazy client init — defers credential validation to first call
- Credential priority: env vars > saved file (
~/.config/google-ads-mcp/credentials.json)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.