SEO MCP
A MCP SEO tool service based on Ahrefs data, offering backlink analysis, keyword research, traffic estimation, and more.
README
SEO MCP
A MCP (Model Control Protocol) SEO tool service based on Ahrefs data. Includes features such as backlink analysis, keyword research, traffic estimation, and more.
Overview
This service provides an API to retrieve SEO data from Ahrefs. It handles the entire process, including solving the CAPTCHA, authentication, and data retrieval. The results are cached to improve performance and reduce API costs.
This MCP service is for educational purposes only. Please do not misuse it. This project is inspired by
@哥飞社群.
Features
-
🔍 Backlink Analysis
- Get detailed backlink data for any domain
- View domain rating, anchor text, and link attributes
- Filter educational and government domains
-
🎯 Keyword Research
- Generate keyword ideas from a seed keyword
- Get keyword difficulty score
- View search volume and trends
-
📊 Traffic Analysis
- Estimate website traffic
- View traffic history and trends
- Analyze popular pages and country distribution
- Track keyword rankings
-
🚀 Performance Optimization
- Use CapSolver to automatically solve CAPTCHA
- Response caching
Installation
Prerequisites
- Python 3.10 or higher
- CapSolver account and API key (register here)
Install from PyPI
pip install seo-mcp
Or use uv:
uv pip install seo-mcp
Manual Installation
-
Clone the repository:
git clone https://github.com/cnych/seo-mcp.git cd seo-mcp -
Install dependencies:
pip install -e . # Or uv pip install -e . -
Set the CapSolver API key:
export CAPSOLVER_API_KEY="your-capsolver-api-key"
Usage
Run the service
You can run the service in the following ways:
Use in Cursor IDE
In the Cursor settings, switch to the MCP tab, click the +Add new global MCP server button, and then input:
{
"mcpServers": {
"SEO MCP": {
"command": "uvx",
"args": ["--python", "3.10", "seo-mcp"],
"env": {
"CAPSOLVER_API_KEY": "CAP-xxxxxx"
}
}
}
}
You can also create a .cursor/mcp.json file in the project root directory, with the same content.
API Reference
The service provides the following MCP tools:
get_backlinks_list(domain: str)
Get the backlinks of a domain.
Parameters:
domain(string): The domain to analyze (e.g. "example.com")
Returns:
{
"overview": {
"domainRating": 76,
"backlinks": 1500,
"refDomains": 300
},
"backlinks": [
{
"anchor": "Example link",
"domainRating": 76,
"title": "Page title",
"urlFrom": "https://referringsite.com/page",
"urlTo": "https://example.com/page",
"edu": false,
"gov": false
}
]
}
keyword_generator(keyword: str, country: str = "us", search_engine: str = "Google")
Generate keyword ideas.
Parameters:
keyword(string): The seed keywordcountry(string): Country code (default: "us")search_engine(string): Search engine (default: "Google")
Returns:
[
{
"keyword": "Example keyword",
"volume": 1000,
"difficulty": 45,
"cpc": 2.5
}
]
get_traffic(domain_or_url: str, country: str = "None", mode: str = "subdomains")
Get the traffic estimation.
Parameters:
domain_or_url(string): The domain or URL to analyzecountry(string): Country filter (default: "None")mode(string): Analysis mode ("subdomains" or "exact")
Returns:
{
"traffic_history": [...],
"traffic": {
"trafficMonthlyAvg": 50000,
"costMontlyAvg": 25000
},
"top_pages": [...],
"top_countries": [...],
"top_keywords": [...]
}
keyword_difficulty(keyword: str, country: str = "us")
Get the keyword difficulty score.
Parameters:
keyword(string): The keyword to analyzecountry(string): Country code (default: "us")
Returns:
{
"difficulty": 45,
"serp": [...],
"related": [...]
}
Development
For development:
git clone https://github.com/cnych/seo-mcp.git
cd seo-mcp
uv sync
How it works
- The user sends a request through MCP
- The service uses CapSolver to solve the Cloudflare Turnstile CAPTCHA
- The service gets the authentication token from Ahrefs
- The service retrieves the requested SEO data
- The service processes and returns the formatted results
Troubleshooting
- CapSolver API key error:Check the
CAPSOLVER_API_KEYenvironment variable - Rate limiting:Reduce request frequency
- No results:The domain may not be indexed by Ahrefs
- Other issues:See GitHub repository
License
MIT License - See LICENSE file
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。