google-ads-kw-mcp
MCP server that exposes Google Ads keyword search volumes to AI agents via the KeywordPlanIdeaService, offering a free alternative to paid keyword-volume APIs.
README
google-ads-kw-mcp
MCP server that exposes Google Ads keyword search volumes to AI agents — a
free alternative to paid keyword-volume APIs, using the same
KeywordPlanIdeaService that powers Google's Keyword Planner.
Why this instead of the official Google Ads MCP?
The official Google Ads MCP talks GAQL/REST and can't query
KeywordPlanIdeaService. This server is complementary, not a duplicate —
use it specifically for search volume, and the official one (or
google-ads-write-mcp) for everything else.
Tools
get_keyword_volumes
Returns search volume data for an array of keywords.
| Param | Type | Default | Description |
|---|---|---|---|
keywords |
list[str] |
required | Max 20 keywords per call |
customer_id |
str |
required | Google Ads account ID (no dashes) |
country |
str |
"ES" |
ISO country code (see list_keyword_countries) |
language |
str |
"es" |
Language code (es, en, fr, de, it, pt, nl, ja, zh, ru, ar) |
Response:
[
{
"keyword": "surf lessons",
"avg_monthly_searches": 480,
"competition": "MEDIUM",
"competition_index": 38,
"low_top_of_page_bid_micros": 206702,
"high_top_of_page_bid_micros": 980973
}
]
list_keyword_countries
Returns the 20 supported countries (ISO code → name).
Setup
You need a Google Ads developer token (Standard Access is enough) and an
OAuth client authorized against your Google Ads MCC/account. If you already
have a google-ads.yaml from the Google Ads API client library, you can
adapt its client_id/client_secret/refresh_token into the JSON format
below.
- Install dependencies:
python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt - Create
~/.config/google-ads-mcp/credentials.json:{ "client_id": "...", "client_secret": "...", "refresh_token": "..." }
MCP client configuration
{
"mcpServers": {
"google-ads-kw": {
"command": "/path/to/.venv/bin/python3",
"args": ["/path/to/google-ads-kw-mcp/server.py"],
"env": {
"GOOGLE_ADS_CREDENTIALS_PATH": "~/.config/google-ads-mcp/credentials.json",
"GOOGLE_ADS_DEVELOPER_TOKEN": "<your developer token>",
"GOOGLE_ADS_LOGIN_CUSTOMER_ID": "<your MCC customer id, no dashes>"
}
}
}
}
| Env var | Purpose |
|---|---|
GOOGLE_ADS_CREDENTIALS_PATH |
Path to the credentials JSON (default: ~/.config/google-ads-mcp/credentials.json) |
GOOGLE_ADS_DEVELOPER_TOKEN |
Your Google Ads developer token |
GOOGLE_ADS_LOGIN_CUSTOMER_ID |
Your MCC/login customer ID, no dashes |
Limits
- Max 20 keywords per call (API limit).
- Long-tail keywords may return
avg_monthly_searches: 0if Google Ads doesn't have enough data. - Free quota is generous (~15,000 ops/day for standard accounts) — plenty for this use case.
License
MIT — see LICENSE.
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.