google-ads-mcp
Enables AI clients to read Google Ads account data through reporting tools for campaigns, ad groups, keywords, and raw GAQL queries, with no write or mutate capabilities.
README
google-ads-mcp
A read-only MCP server for the Google Ads API. It exposes reporting tools (campaigns, ad groups, keywords, and raw GAQL queries) so an MCP client (Claude Code, Claude Desktop, etc.) can query your Google Ads account. There are no mutate/write tools — this server cannot change campaigns, budgets, or bids.
Tools
| Tool | Description |
|---|---|
list_accessible_customers |
List customer IDs accessible to the configured credentials. |
get_account_hierarchy |
List accounts under a manager (MCC) account. |
list_campaigns |
List campaigns and their settings (no metrics). |
get_campaign_performance |
Campaign-level metrics (impressions, clicks, cost, conversions). |
get_ad_group_performance |
Ad group-level metrics. |
get_keyword_performance |
Keyword-level metrics. |
run_gaql |
Run a raw read-only GAQL SELECT query. |
Prerequisites
You need Google Ads API credentials:
- A developer token from the Google Ads API Center (Tools & Settings → API Center) on the manager account you'll authenticate with.
- An OAuth2 client ID / client secret from a Google Cloud project with the Google Ads API enabled.
- A refresh token for a user with access to the target account(s). See
Google's OAuth desktop flow guide
or run the helper script bundled with the
google-adsPython library. - If you authenticate via a manager (MCC) account on behalf of a client
account, its
login_customer_id.
Setup
# from the repo root
pip install -e .
Configure credentials one of two ways:
Option A: YAML file
cp google-ads.yaml.example google-ads.yaml
# edit google-ads.yaml with your values
Option B: environment variables
cp .env.example .env
# edit .env, then export the variables into your shell environment
Either google-ads.yaml in the current directory, or the GOOGLE_ADS_*
environment variables, will be picked up automatically. Set
GOOGLE_ADS_CONFIGURATION_FILE_PATH to point at a YAML file in a different
location if you'd prefer.
Running standalone
python -m google_ads_mcp
# or, after `pip install -e .`:
google-ads-mcp
The server communicates over stdio, per the MCP spec.
Registering with an MCP client
Claude Code (project-level .mcp.json, or claude mcp add):
{
"mcpServers": {
"google-ads": {
"command": "google-ads-mcp",
"env": {
"GOOGLE_ADS_CONFIGURATION_FILE_PATH": "/absolute/path/to/google-ads.yaml"
}
}
}
}
Claude Desktop (claude_desktop_config.json): same mcpServers entry as
above.
Security notes
- This server only issues GAQL
SELECTqueries viaGoogleAdsService.SearchStream. GAQL has noINSERT/UPDATE/DELETEsyntax, so there is no way to mutate Google Ads data through these tools. - Never commit
google-ads.yamlor.env— both are gitignored. Treat your developer token, OAuth client secret, and refresh token as credentials. customer_idand entity IDs are validated as numeric before being interpolated into GAQL query strings.
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.