by cnych
A free SEO tool MCP (Model Control Protocol) service based on Ahrefs data, offering features like backlink analysis, keyword research, and traffic estimation.
SEO MCP is a free Model Control Protocol (MCP) service designed to provide SEO data based on Ahrefs. It acts as an API to retrieve various SEO metrics, handling complex processes like CAPTCHA solving, authentication, and data retrieval. The service also incorporates caching to enhance performance and minimize API costs.
To use SEO MCP, you first need to install it. You can install it via pip or uv:
pip install seo-mcp
# Or
uv pip install seo-mcp
Alternatively, you can clone the repository and install it manually:
git clone https://github.com/cnych/seo-mcp.git
cd seo-mcp
pip install -e .
# Or
uv pip install -e .
Before running, ensure you have Python 3.10 or higher and set your CapSolver API key as an environment variable:
export CAPSOLVER_API_KEY="your-capsolver-api-key"
You can run the service within the Cursor IDE by adding it to your MCP server settings or by creating a .cursor/mcp.json
file in your project root. The service provides several API endpoints for different SEO functionalities:
get_backlinks_list(domain: str)
: Retrieves backlink data for a given domain.keyword_generator(keyword: str, country: str = "us", search_engine: str = "Google")
: Generates keyword ideas.get_traffic(domain_or_url: str, country: str = "None", mode: str = "subdomains")
: Estimates website traffic.keyword_difficulty(keyword: str, country: str = "us")
: Gets the keyword difficulty score.SEO MCP offers a comprehensive set of features for SEO analysis:
SEO MCP is ideal for:
Q: What is Ahrefs data? A: Ahrefs is a popular SEO toolset that provides data on backlinks, keywords, organic search traffic, and more. SEO MCP leverages this data.
Q: Is SEO MCP truly free? A: Yes, SEO MCP is a free service, but it requires a CapSolver account and API key for CAPTCHA solving, which may incur costs depending on your usage.
Q: What if I encounter a "CapSolver API key error"?
A: Ensure that your CAPSOLVER_API_KEY
environment variable is correctly set.
Q: Why am I experiencing "Rate limiting"? A: This could be due to sending too many requests in a short period. Try reducing your request frequency.
Q: What if I get "No results" for a domain? A: The domain you are querying might not be indexed by Ahrefs.
Q: Is this project for commercial use? A: The project states it is for educational purposes only and advises against misuse. Please refer to the MIT License for more details.
A MCP (Model Control Protocol) SEO tool service based on Ahrefs data. Includes features such as backlink analysis, keyword research, traffic estimation, and more.
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
.
🔍 Backlink Analysis
🎯 Keyword Research
📊 Traffic Analysis
🚀 Performance Optimization
pip install seo-mcp
Or use uv
:
uv pip install seo-mcp
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"
You can run the service in the following ways:
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.
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": [...]
}
For development:
git clone https://github.com/cnych/seo-mcp.git
cd seo-mcp
uv sync
CAPSOLVER_API_KEY
environment variableMIT License - See LICENSE file
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by firecrawl
Adds powerful web scraping, crawling, and search capabilities to LLM clients through a Model Context Protocol (MCP) server.
by mendableai
Firecrawl MCP Server is an official Model Context Protocol (MCP) server implementation that integrates with Firecrawl to provide powerful web scraping capabilities to Large Language Models (LLMs). It acts as a bridge between LLMs and the web, allowing them to access and process web content for various tasks.
by tavily-ai
Provides real-time web search, intelligent data extraction, site mapping, and crawling capabilities via MCP tools.
by iFurySt
RedNote-MCP is an MCP server designed to access content from RedNote (XiaoHongShu, xhs), a popular Chinese social media and e-commerce platform. It enables programmatic interaction with RedNote for data retrieval and automation.
by zcaceres
fetch-mcp is a flexible HTTP fetching server designed to retrieve web content in various formats. It acts as a server that can fetch HTML, JSON, Markdown, or plaintext from specified URLs, enabling on-demand fetching and transformation of web content.
by apify
An MCP server for Apify Actors, allowing AI assistants to use any of the 3,000+ pre-built cloud tools for web scraping and automation.
by openbnb-org
The mcp-server-airbnb is an MCP (Multi-Cloud Platform) server designed to interact with Airbnb. It provides tools for searching Airbnb listings and retrieving detailed information about specific listings.
by tinyfish-io
AgentQL MCP Server is a Model Context Protocol (MCP) server that integrates AgentQL's data extraction capabilities, enabling AI agents to get structured data from the unstructured web.
by oxylabs
Bridge AI models and the internet, delivering clean, structured data from any website through a single API.