Backlinks MCP
Handles solving Cloudflare Turnstile CAPTCHA automatically to access protected SEO data services.
Provides access to Google's search engine for keyword research, analysis, and SEO optimization through the MCP service.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Backlinks MCP get backlinks for example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: Sitemap MCP Server
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-mcpOr use uv:
uv pip install seo-mcpManual Installation
Clone the repository:
git clone https://github.com/cnych/seo-mcp.git cd seo-mcpInstall 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 syncHow 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 variableRate 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
Available Tools
4 toolsget_backlinks_listA
Get backlinks list for the specified domain
Args:
domain (str): The domain to query
Returns:
List of backlinks for the domain, containing title, URL, domain rating, etc.
Inputs: domain (required).
get_trafficC
Check the estimated search traffic for any website.
Args:
domain_or_url (str): The domain or URL to query
country (str): The country to query, default is "None"
mode (["subdomains", "exact"]): The mode to use for the query
Returns:
Traffic data for the specified domain or URL
Inputs: domain_or_url (required), country, mode.
keyword_difficultyC
Get keyword difficulty for the specified keyword
Inputs: keyword (required), country.
keyword_generatorC
Get keyword ideas for the specified keyword
Inputs: keyword (required), country, search_engine.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap. get_backlinks_list retrieves backlink data for domains, get_traffic provides traffic estimates, keyword_difficulty assesses keyword competitiveness, and keyword_generator suggests related keywords. The four tools cover separate aspects of SEO analysis without ambiguity.
All tool names follow a consistent verb_noun pattern with snake_case formatting. Each name clearly indicates its function: get_backlinks_list, get_traffic, keyword_difficulty, and keyword_generator maintain perfect naming consistency throughout the set.
Four tools is reasonable for an SEO/backlink analysis server, though slightly minimal. The tools cover core SEO functions (backlinks, traffic, keyword difficulty, keyword generation), but additional tools like domain authority checking or competitor analysis could enhance completeness. The count is appropriate but leaves room for expansion.
The tool set covers key SEO analysis areas but has notable gaps. While it provides backlink data, traffic estimates, and keyword tools, it lacks domain authority metrics, competitor backlink analysis, and link-building tools. Agents can perform basic SEO analysis but may encounter dead ends for more advanced workflows requiring these missing operations.
Maintenance
Related MCP Connectors
SEO MCP server — backlinks, domain authority, tech stack, and 18+ tools via Common Crawl.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
SEO MCP server for keyword research, live SERPs, backlinks, site audits and AI visibility.
Related MCP Servers
- FlicenseBqualityDmaintenanceAn MCP Server for Web scraping and Crawling, built using Crawl4AI224-
- AlicenseBqualityDmaintenanceMCP server for fetching, parsing and crawling sitemaps of a given website4157 PyPI8MIT
- AlicenseBqualityCmaintenanceMCP server & CLI for keyword research, domain analytics, backlinks, traffic analysis, and competitive intelligence using Semrush API data.7740MIT
- AlicenseAqualityDmaintenanceMCP server for Common Crawl CDX that enables backlink discovery, expired domain finding, and competitor gap analysis without requiring API keys.42MIT