Keyword Research MCP
Keyword Research MCP
Keyword Research MCP 是一个轻量级的本地 MCP 服务器,用于检索和规范化 Google Ads 关键词规划证据。它正在积极开发中;当前仓库包含可执行的项目基础,以及类型化、经过测试的研究接口和生产级 Google Ads 适配器。实现计划中描述的 MCP 工具注册仍在构建中。
Google Ads 中的付费竞争描述的是广告主活动。本项目不将其呈现为自然排名难度,也不计算综合关键词得分。
环境要求
Python 3.10 至 3.14
测试不需要 Google Ads 凭据。当生产适配器连接到 Google Ads 时,才需要这些凭据。
Related MCP server: Google Ads MCP Server
Google Ads 配置
生产适配器使用 google-ads==31.2.0,并明确选择 Google Ads API v25。请配置恰好一个目标客户和一种身份验证方法。客户 ID 可能包含连字符;它们会在内存中被规范化。
对于用户 OAuth,请设置:
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"对于服务账号,请省略三个用户 OAuth 设置,并设置:
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或者,将 GOOGLE_ADS_CONFIGURATION_FILE_PATH 指向本地的 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可选进程设置为 KEYWORD_RESEARCH_CACHE_CAPACITY(默认 128)和 KEYWORD_RESEARCH_LOG_LEVEL(默认 INFO)。凭据文件、google-ads.yaml 和 .env 文件会被 Git 忽略。
设置并运行
uv sync
uv run keyword-research-mcp该命令通过 stdio 运行,因此它会静默等待 MCP 客户端,并且只向标准输出写入协议消息。
开发
运行与 CI 中相同的质量检查:
uv run ruff format --check .
uv run ruff check .
uv run pyright
uv run pytest
uv build有关预期的工具契约、架构、交付阶段和产品边界,请参阅实现计划。
许可证
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables comprehensive Google Ads campaign management and analytics through the Google Ads API. Supports querying campaigns, ad groups, keywords, performance metrics, and executing custom GAQL queries with token-efficient implementation.
- AlicenseNot gradedqualityAmaintenanceEnables Large Language Models to interact with Google Ads API for querying campaigns, ad groups, and performing mutations like creating budgets and ads.230Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to query Google Ads accounts, search for information, and list accessible customers.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents and LLMs to interact with Google Ads accounts, allowing search, retrieval of resource metadata, and listing accessible customers via the Google Ads API.Apache 2.0
Related MCP Connectors
Manage Google, Microsoft, TikTok and LinkedIn Ads from Claude or ChatGPT. Writes need approval.
Google Ads, Meta (Facebook) Ads, GA4 and Merchant Center analysis in plain language. Read-only.
AI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pccaza/keyword-research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server