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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。