How do I use SEO Research MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SEO Research MCP analyze backlinks for openai.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 Research MCP

by iflow-mcp

Overview Schema Source Related Servers Discussions Admin

Local

SEO Research MCP

Free SEO research tools for AI-powered IDEs

Python 3.10+ License: MIT MCP

Features • Installation • IDE Setup • API Reference • Contributing • Credits

CAUTION

⚠️ Educational Use Only

This project is for educational and research purposes only.

This tool interfaces with third-party services (Ahrefs, CapSolver)
Users must comply with all applicable terms of service
The authors do not endorse any use that violates third-party ToS
Use responsibly and at your own risk

By using this software, you acknowledge that you understand and accept these terms.

Related MCP server: SEO Research MCP

🎯 What is this?

SEO Research MCP brings powerful SEO research capabilities directly into your AI coding assistant. Using the Model Context Protocol (MCP), it connects your IDE to Ahrefs' SEO data, allowing you to:

Research competitor backlinks while coding
Generate keyword ideas without leaving your editor
Analyze traffic patterns for any website
Check keyword difficulty before creating content

✨ Features

Feature	Description	Example Use
🔗 Backlink Analysis	Domain rating, anchor text, edu/gov links	"Show me backlinks for competitor.com"
🔑 Keyword Research	Generate ideas from seed keywords	"Find keywords related to 'python tutorial'"
📊 Traffic Analysis	Monthly traffic, top pages, countries	"What's the traffic for example.com?"
📈 Keyword Difficulty	KD score with full SERP breakdown	"How hard is 'best laptop 2025' to rank for?"

📋 Prerequisites

Before you start, you'll need:

Python 3.10 or higher
```
python --version  # Should be 3.10+
```
CapSolver API Key (for CAPTCHA solving)
👉 Get your API key here

📦 Installation

Option 1: From PyPI (Recommended)

pip install seo-mcp

Or using uv:

uv pip install seo-mcp

Option 2: From Source

git clone https://github.com/egebese/seo-research-mcp.git
cd seo-research-mcp
pip install -e .

🛠️ IDE Setup Guides

Choose your IDE and follow the setup instructions:

Step 1: Open Config File

Open Claude Desktop
Go to Settings → Developer → Edit Config

Step 2: Add Configuration

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "seo-research": {
      "command": "uvx",
      "args": ["--python", "3.10", "seo-mcp"],
      "env": {
        "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Step 3: Restart & Verify

Restart Claude Desktop
Look for the hammer/tools icon in the bottom-right corner

📁 Config file locations:

OS	Path
macOS	`~/Library/Application Support/Claude/claude_desktop_config.json`
Windows	`%APPDATA%\Claude\claude_desktop_config.json`

Option A: Quick Setup (CLI)

# Add the MCP server
claude mcp add seo-research --scope user -- uvx --python 3.10 seo-mcp

# Set your API key
export CAPSOLVER_API_KEY="YOUR_API_KEY_HERE"

Option B: Config File

Add to ~/.claude.json:

{
  "mcpServers": {
    "seo-research": {
      "command": "uvx",
      "args": ["--python", "3.10", "seo-mcp"],
      "env": {
        "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Verify Installation

claude mcp list

Global Setup (All Projects)

Create ~/.cursor/mcp.json:

{
  "mcpServers": {
    "seo-research": {
      "command": "uvx",
      "args": ["--python", "3.10", "seo-mcp"],
      "env": {
        "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Project Setup (Single Project)

Create .cursor/mcp.json in your project root with the same content.

Verify Installation

Go to File → Preferences → Cursor Settings
Select MCP in the sidebar
Check that seo-research appears under Available Tools

Step 1: Open Settings

Mac: Cmd + Shift + P → "Open Windsurf Settings"
Windows/Linux: Ctrl + Shift + P → "Open Windsurf Settings"

Step 2: Add Configuration

Navigate to Cascade → MCP Servers → Edit raw mcp_config.json:

{
  "mcpServers": {
    "seo-research": {
      "command": "uvx",
      "args": ["--python", "3.10", "seo-mcp"],
      "env": {
        "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

📁 Config location: ~/.codeium/windsurf/mcp_config.json

⚠️ Requires VS Code 1.102+ with GitHub Copilot

Setup

Create .vscode/mcp.json in your workspace:

{
  "servers": {
    "seo-research": {
      "command": "uvx",
      "args": ["--python", "3.10", "seo-mcp"],
      "env": {
        "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Activate

Open the .vscode/mcp.json file
Click the Start button that appears
In Chat view, click Tools to toggle MCP tools
Use #tool_name in prompts to invoke tools

Setup

Add to your Zed settings.json:

{
  "context_servers": {
    "seo-research": {
      "command": {
        "path": "uvx",
        "args": ["--python", "3.10", "seo-mcp"],
        "env": {
          "CAPSOLVER_API_KEY": "YOUR_API_KEY_HERE"
        }
      }
    }
  }
}

Verify

Open Agent Panel settings
Check the indicator dot next to seo-research
Green dot = Server is active

📖 API Reference

`get_backlinks_list(domain)`

Get backlink data for any domain.

# Input
domain: str  # e.g., "example.com"

# Output
{
  "overview": {
    "domainRating": 76,
    "backlinks": 1500,
    "refDomains": 300
  },
  "backlinks": [
    {
      "anchor": "Example link",
      "domainRating": 76,
      "title": "Page title",
      "urlFrom": "https://source.com/page",
      "urlTo": "https://example.com/page",
      "edu": false,
      "gov": false
    }
  ]
}

`keyword_generator(keyword, country?, search_engine?)`

Generate keyword ideas from a seed keyword.

# Input
keyword: str        # Seed keyword
country: str        # Default: "us"
search_engine: str  # Default: "Google"

# Output
[
  {
    "keyword": "example keyword",
    "volume": 1000,
    "difficulty": 45
  }
]

`get_traffic(domain_or_url, country?, mode?)`

Estimate search traffic for a website.

# Input
domain_or_url: str  # Domain or full URL
country: str        # Default: "None" (all countries)
mode: str           # "subdomains" | "exact"

# Output
{
  "traffic": {
    "trafficMonthlyAvg": 50000,
    "costMontlyAvg": 25000
  },
  "top_pages": [...],
  "top_countries": [...],
  "top_keywords": [...]
}

`keyword_difficulty(keyword, country?)`

Get keyword difficulty score with SERP analysis.

# Input
keyword: str   # Keyword to analyze
country: str   # Default: "us"

# Output
{
  "difficulty": 45,
  "serp": [...]
}

⚙️ How It Works

┌──────────────┐     ┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│     Your     │     │   CapSolver  │     │    Ahrefs    │     │   Formatted  │
│    AI IDE    │────▶│   (CAPTCHA)  │────▶│     API      │────▶│    Results   │
└──────────────┘     └──────────────┘     └──────────────┘     └──────────────┘

Request → Your AI assistant calls an MCP tool
CAPTCHA → CapSolver handles Cloudflare verification
Data → Ahrefs API returns SEO data
Response → Formatted results appear in your IDE

🐛 Troubleshooting

Problem	Solution
"CapSolver API key error"	Check `CAPSOLVER_API_KEY` is set correctly
Rate limiting	Wait a few minutes, reduce request frequency
No results	Domain may not be indexed by Ahrefs
Server not appearing	Restart your IDE after config changes
Connection timeout	Check your internet connection

🤝 Contributing

Contributions are welcome! Here's how you can help:

Ways to Contribute

🐛 Report Bugs - Found an issue? Open a bug report
💡 Suggest Features - Have an idea? Request a feature
📝 Improve Docs - Fix typos, clarify instructions, add examples
🔧 Submit Code - Bug fixes, new features, optimizations

Development Setup

# Clone the repo
git clone https://github.com/egebese/seo-research-mcp.git
cd seo-research-mcp

# Install dependencies
uv sync

# Run locally
python main.py

Pull Request Process

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to your branch (git push origin feature/amazing-feature)
Open a Pull Request

Code Guidelines

Keep code simple and readable
Add comments for complex logic
Test your changes before submitting
Follow existing code style

📊 Star History

📄 License

This project is licensed under the MIT License with an educational use notice.

See LICENSE for full details.

🙏 Credits

This project is a fork of seo-mcp by @cnych.

Special thanks to the original author for creating this tool.

⭐ If this helps your SEO research, consider giving it a star! ⭐

Available Tools

4 tools

get_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.

ParametersJSON Schema

Name	Required	Description	Default
`domain`	Yes

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes return type and fields (title, URL, domain rating). No annotations provided, so description carries burden; it is transparent about the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise, all sentences contribute value. Front-loaded purpose with immediate clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter, the description covers purpose, input, and output sufficiently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage 0%; description adds 'The domain to query' which is minimal. Provides no additional context like format or examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb and resource: 'Get backlinks list for the specified domain'. Distinguishes from sibling tools like get_traffic and keyword_difficulty.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use. Implied usage for domain backlinks, but no guidance on alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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

ParametersJSON Schema

Name	Required	Default
`domain_or_url`	Yes
`country`	No	None
`mode`	No	subdomains

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It does not disclose whether the tool is read-only, destructive, requires authentication, or has rate limits. For a data query tool, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences plus an Args/Returns list. It is front-loaded with the purpose and structured for easy scanning. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description only vaguely states 'Traffic data' without specifying structure. Combined with missing behavioral context, the description is incomplete for a 3-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description includes an Args section that lists parameters and their types, adding some meaning beyond the schema (e.g., domain_or_url is 'The domain or URL to query'). However, it does not explain the difference between 'subdomains' and 'exact' modes, nor the effect of the country parameter, beyond default values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Check the estimated search traffic for any website', which clearly identifies the verb and resource. It distinguishes from sibling tools like get_backlinks_list and keyword_difficulty by focusing on traffic estimation, but does not explicitly differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it specify prerequisites or exclusions. It simply states the tool's function without context for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

keyword_difficultyC

Get keyword difficulty for the specified keyword

ParametersJSON Schema

Name	Required	Description	Default
`keyword`	Yes
`country`	No		us

TDQS

C2.6/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must carry full burden. It does not disclose how difficulty is calculated, what unit/scale is used, or any side effects. Bare minimum.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 8 words is concise but lacks substance. Appropriate length for the content, but more detail would improve informativeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 2 params requiring explanation, the description is inadequate. Leaves agent guessing about return values, scope, and usage nuances.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage. Description only mentions 'specified keyword' without explaining its meaning or format. Country parameter and default are not explained. Adds minimal value to schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get keyword difficulty for the specified keyword' clearly states the action and resource. It is distinct from sibling tools like get_backlinks_list and get_traffic, though sibling differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool compared to alternatives. Lacks context about prerequisites or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

keyword_generatorC

Get keyword ideas for the specified keyword

ParametersJSON Schema

Name	Required	Default
`keyword`	Yes
`country`	No	us
`search_engine`	No	Google

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. Description only says 'get ideas' with no disclosure of behavior (e.g., return format, rate limits, data source).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely short, no fluff, but lacks essential details. Conciseness is achieved at the expense of completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 3 parameters, no output schema, and no annotations, the description is severely incomplete. No information on return values or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and description only mentions the keyword parameter, ignoring country and search_engine. Fails to compensate for missing parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns keyword ideas for a given keyword. It distinguishes from sibling tools (backlinks, traffic, difficulty) but lacks specificity about the output format or scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs. alternatives, no prerequisites, no context about typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.2.4May 31, 2026
- First observedget_backlinks_list
- First observedget_traffic
- First observedkeyword_difficulty
- First observedkeyword_generator

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored 2026-05-31 15:15 across 4 tools

Disambiguation5/5

Each tool targets a distinct SEO aspect: backlinks, traffic, keyword difficulty, and keyword generation. No overlap in functionality.

Naming Consistency3/5

Two tools use 'get_' prefix (get_backlinks_list, get_traffic) while two use 'keyword_' prefix (keyword_difficulty, keyword_generator), creating an inconsistent pattern.

Tool Count4/5

Four tools is a reasonable size for a focused SEO research server, covering core tasks without being bloated.

Completeness3/5

Covers backlinks, traffic, and keyword analysis but missing common SEO features like domain overview or competitor analysis, leaving minor gaps.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

VibeSEOOAuth
dev.vibeseo
SEO research, audits, backlinks, GSC, and content workflow tools for AI agents.
Marketing Search
22
ahrefs C
com.jojapi
Ahrefs: Ahrefs API: SEO powerhouse featuring keyword research, backlink analysis, and SERP tracking.
Marketing Research & Data
111
EzBiz SEO & Marketing Analysis A
com.ezbizservices
AI-powered SEO and marketing: keyword research, SERP analysis, and content optimization tools.
Marketing Search Web Scraping
2
MetrifyrOAuth
cloud.metrifyr
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
Monitoring Search Marketing
2

Related MCP Servers

DataForSEO MCP Server
Marketing Search Web Scraping
cortex8
-
license
C
quality
Not graded
maintenance
Enables AI assistants to access comprehensive SEO data through DataForSEO APIs, including SERP results, keyword research, backlink analysis, on-page metrics, and domain analytics. Supports real-time search engine data from Google, Bing, and Yahoo with customizable filtering and multiple deployment options.
Updated a year ago (2025-10-13 00:32 UTC)
36
-
SEO Research MCP
Marketing Search Developer Tools
egebese
A
license
B
quality
C
maintenance
Enables AI coding assistants to perform SEO research tasks including backlink analysis, keyword research, traffic estimation, and keyword difficulty analysis using Ahrefs data directly within IDEs.
Updated 2 months ago (2026-07-06 20:52 UTC)
4
191
MIT
SEO Insights MCP Server
Marketing Search
mrgoonie
A
license
Not graded
quality
F
maintenance
Connects AI assistants to SEO APIs for backlinks analysis, keyword research, and traffic analysis.
Updated 10 months ago (2025-11-24 18:08 UTC)
7 npm
28
MIT
advanced-seo-mcp
Marketing Web Scraping
halilertekin
A
license
A
quality
D
maintenance
Provides AI agents with professional-grade SEO capabilities including on-page analysis, technical audits, PageSpeed insights, and Ahrefs data integration.
Updated 4 months ago (2026-05-22 22:37 UTC)
13
8 npm
5
MIT