About Backlinks Mcp
Backlinks Mcp is an MCP service for retrieving Ahrefs-based SEO data, aimed at SEO analysis and keyword research. It handles CAPTCHA and authentication, and caches results.
Key features
- 01Domain backlink analysis
- 02Keyword ideas and difficulty scores
- 03Traffic estimates and trends
- 04CapSolver CAPTCHA handling
- 05Response caching
Use cases
- 01Review a domain’s backlinks and anchor text
- 02Generate keyword ideas from a seed
- 03Inspect site traffic and popular pages
MCP support
It exposes tools for MCP clients to retrieve Ahrefs SEO data, including backlink, keyword, and traffic analysis.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESEO 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.