Keyword Research MCP
Enables retrieval and normalization of Google Ads keyword-planning evidence.
README
Keyword Research MCP
Keyword Research MCP is a lightweight local MCP server for retrieving and normalizing Google Ads keyword-planning evidence. It is under active development; the current repository contains the executable project foundation plus the typed, tested research interface and production Google Ads adapter. MCP tool registration described in the implementation plan is still being built.
Paid Competition in Google Ads describes advertiser activity. This project does not present it as organic ranking difficulty and does not calculate a composite keyword score.
Requirements
- Python 3.10 through 3.14
- uv
Google Ads credentials are not needed for tests. They are required when the production adapter connects to Google Ads.
Google Ads configuration
The production adapter uses google-ads==31.2.0 and explicitly selects Google
Ads API v25. Configure exactly one target customer and one authentication
method. Customer IDs may contain hyphens; they are normalized in memory.
For user OAuth, set:
export GOOGLE_ADS_DEVELOPER_TOKEN="developer-token-placeholder"
export GOOGLE_ADS_CUSTOMER_ID="123-456-7890"
export GOOGLE_ADS_LOGIN_CUSTOMER_ID="987-654-3210" # optional manager account
export GOOGLE_ADS_CLIENT_ID="client-id-placeholder"
export GOOGLE_ADS_CLIENT_SECRET="client-secret-placeholder"
export GOOGLE_ADS_REFRESH_TOKEN="refresh-token-placeholder"
For a service account, omit the three user-OAuth settings and set:
export GOOGLE_ADS_DEVELOPER_TOKEN="developer-token-placeholder"
export GOOGLE_ADS_CUSTOMER_ID="123-456-7890"
export GOOGLE_ADS_JSON_KEY_FILE_PATH="/path/to/service-account.json"
export GOOGLE_ADS_IMPERSONATED_EMAIL="ads-user@example.test" # optional
Alternatively, point GOOGLE_ADS_CONFIGURATION_FILE_PATH at a local
google-ads.yaml:
developer_token: developer-token-placeholder
customer_id: "123-456-7890"
login_customer_id: "987-654-3210"
client_id: client-id-placeholder
client_secret: client-secret-placeholder
refresh_token: refresh-token-placeholder
Optional process settings are KEYWORD_RESEARCH_CACHE_CAPACITY (default 128)
and KEYWORD_RESEARCH_LOG_LEVEL (default INFO). Credential files,
google-ads.yaml, and .env files are ignored by Git.
Set up and run
uv sync
uv run keyword-research-mcp
The command runs over stdio, so it waits silently for an MCP client and writes
protocol messages only to standard output.
Development
Run the same quality gate used in CI:
uv run ruff format --check .
uv run ruff check .
uv run pyright
uv run pytest
uv build
See the implementation plan for the intended tool contracts, architecture, delivery phases, and product boundaries.
License
MIT
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。