mcp-google-ads
Multi-account Google Ads MCP server that allows connecting any number of Google Ads accounts and querying campaign performance, keywords, search terms, and account analytics by name in the same session.
README
mcp-google-ads
Multi-account Google Ads MCP server. Connect any number of Google Ads accounts to Claude, Cursor, Codex, or any MCP-compatible AI assistant — query campaign performance, keywords, search terms, and account analytics by name in the same session.
# Install: uvx mcp-google-ads-multi
# Ask your AI:
"Show me campaign performance for account my-client last month"
"What search terms drove conversions for client-acme in Q2?"
"Compare my-account's spend between January and February"
"Which keywords have quality scores below 5 for campaign 123?"
Why this one?
Most Google Ads MCP servers support one account per server process. This one lets you configure multiple accounts and switch between them per tool call — no restart needed.
| Feature | This server | Others |
|---|---|---|
| Multiple accounts | Yes — named, switchable | No — one per process |
| OAuth + service account | Both, mixed per account | Usually one type |
| Quality score data | Yes | Rarely |
| Search terms report | Yes | Sometimes |
| Rate limit retry | Yes — exponential backoff | No |
| SSE transport (remote) | Yes | Varies |
Quickstart
1. Get a developer token — apply at Google Ads API Center (free, ~3 business days)
2. Create OAuth credentials — Google Cloud Console → Enable Google Ads API → Credentials → OAuth client ID → Desktop app
3. Create your accounts config:
mkdir -p ~/.config/mcp-google-ads
cp accounts.example.json ~/.config/mcp-google-ads/accounts.json
# Edit it — add your accounts
4. Add to your MCP client config:
{
"mcpServers": {
"google-ads": {
"command": "uvx",
"args": ["mcp-google-ads-multi"],
"env": {
"GOOGLE_ADS_DEVELOPER_TOKEN": "your-developer-token",
"GOOGLE_ADS_ACCOUNTS_CONFIG": "/Users/you/.config/mcp-google-ads/accounts.json"
}
}
}
}
5. Restart your AI client. Done.
Accounts config
{
"default": "my-account",
"accounts": {
"my-account": {
"type": "oauth",
"client_id": "YOUR_CLIENT_ID.apps.googleusercontent.com",
"client_secret": "YOUR_CLIENT_SECRET",
"token_file": "~/.config/mcp-google-ads/my-account.token"
},
"client-acme": {
"type": "oauth",
"client_id": "YOUR_CLIENT_ID.apps.googleusercontent.com",
"client_secret": "YOUR_CLIENT_SECRET",
"token_file": "~/.config/mcp-google-ads/client-acme.token"
}
}
}
Set GOOGLE_ADS_DEVELOPER_TOKEN in your environment. All other credentials stay local.
Available tools
| Tool | What it does |
|---|---|
list_accounts |
Show all configured accounts |
set_default_account |
Change the default account |
list_customers |
List all accessible Google Ads accounts under your login |
get_account_summary |
Total clicks, cost, conversions for a period |
list_campaigns |
All campaigns with status, budget, 30-day metrics |
get_campaign_performance |
Campaign metrics for any date range |
compare_periods |
Two date ranges side-by-side with deltas |
get_keyword_performance |
Keyword metrics + quality scores |
search_terms_report |
Actual search queries that triggered your ads |
get_ad_performance |
Ad-level CTR and conversions |
Environment variables
| Variable | Default | Description |
|---|---|---|
GOOGLE_ADS_DEVELOPER_TOKEN |
required | Your Google Ads API developer token |
GOOGLE_ADS_ACCOUNTS_CONFIG |
~/.config/mcp-google-ads/accounts.json |
Path to accounts config |
MCP_TRANSPORT |
stdio |
Set to sse for remote deployment |
MCP_HOST |
127.0.0.1 |
SSE bind host |
MCP_PORT |
3001 |
SSE bind port |
License
MIT
<!-- mcp-name: io.github.Ayo-Fam/mcp-google-ads -->
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。