Seo Mcp

What is Seo Mcp about?

Seo Mcp delivers an MCP‑based API that queries Ahrefs for SEO metrics such as backlinks, keyword ideas, traffic estimates, and keyword difficulty. It handles Cloudflare Turnstile CAPTCHA automatically via CapSolver and caches results to reduce cost and latency.

How to use Seo Mcp?

1. Install the package (pip install seo-mcp or uv pip install seo-mcp).
2. Export your CapSolver API key:

   export CAPSOLVER_API_KEY="your-capsolver-api-key"
   

3. Start the MCP server (e.g., via uvx --python 3.10 seo-mcp).
4. Call the provided MCP tools (get_backlinks_list, keyword_generator, get_traffic, keyword_difficulty) from your client.

Key Features of Seo Mcp

• Backlink Analysis: Retrieve detailed backlink data, domain rating, anchor text, and filter educational/government links.
• Keyword Research: Generate keyword ideas, view search volume, difficulty, CPC, and related terms.
• Traffic Estimation: Get monthly traffic averages, historic trends, top pages, countries, and keywords.
• Keyword Difficulty: Score difficulty and see SERP snapshots and related keywords.
• CAPTCHA Automation: Uses CapSolver to solve Cloudflare Turnstile automatically.
• Response Caching: Reduces duplicate requests and Ahrefs API costs.

Use Cases of Seo Mcp

• SEO Audits: Quickly pull backlink profiles and traffic data for competitor analysis.
• Content Planning: Generate high‑volume, low‑difficulty keyword lists for content creators.
• Marketing Dashboards: Feed traffic estimations and top‑page data into reporting tools.
• Automated SEO Monitoring: Schedule regular calls to track ranking and backlink changes.

FAQ from the Seo Mcp

• What Ahrefs plan is required? A valid Ahrefs account with API access is needed; the service handles authentication automatically.
• Do I need a CapSolver account? Yes, a CapSolver API key is required to solve the Cloudflare Turnstile CAPTCHA.
• How is data cached? Results are stored in memory for a configurable period (default is a few minutes) to limit repeat API calls.
• Can I change the Python version? The service requires Python 3.10+; you may specify a different minor version when launching with uvx.
• What if I hit Ahrefs rate limits? Reduce request frequency or upgrade your Ahrefs subscription; the service will return an error indicating the limit.

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:

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

2. Install dependencies:

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

3. 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 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