MCPcopy Index your code
hub / github.com/cnych/seo-mcp

github.com/cnych/seo-mcp @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
19 symbols 84 edges 7 files 16 documented · 84%
What it actually does AI analysis from the code graph — generated when you open this
loading…
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.

中文

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

  1. Clone the repository:

bash git clone https://github.com/cnych/seo-mcp.git cd seo-mcp

  1. Install dependencies:

bash pip install -e . # Or uv pip install -e .

  1. Set the CapSolver API key:

bash 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 keyword
  • country (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 analyze
  • country (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 analyze
  • country (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

  1. The user sends a request through MCP
  2. The service uses CapSolver to solve the Cloudflare Turnstile CAPTCHA
  3. The service gets the authentication token from Ahrefs
  4. The service retrieves the requested SEO data
  5. The service processes and returns the formatted results

Troubleshooting

  • CapSolver API key error:Check the CAPSOLVER_API_KEY environment 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

Core symbols most depended-on inside this repo

get_capsolver_token
called by 4
src/seo_mcp/server.py
main
called by 1
main.py
check_traffic
called by 1
src/seo_mcp/traffic.py
iso_to_timestamp
called by 1
src/seo_mcp/backlinks.py
save_signature_to_cache
called by 1
src/seo_mcp/backlinks.py
load_signature_from_cache
called by 1
src/seo_mcp/backlinks.py
get_signature_and_overview
called by 1
src/seo_mcp/backlinks.py
format_backlinks
called by 1
src/seo_mcp/backlinks.py

Shape

Function 19

Languages

Python100%

Modules by API surface

src/seo_mcp/backlinks.py7 symbols
src/seo_mcp/server.py6 symbols
src/seo_mcp/keywords.py3 symbols
src/seo_mcp/traffic.py1 symbols
src/seo_mcp/logger.py1 symbols
main.py1 symbols

For agents

$ claude mcp add seo-mcp \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

Ask about this repo answers extend the page