How do I use SEO Research MCP?

1. Click on "Install 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 Related Servers Score Discussions

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_listB

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

B3.2/5.0

Behavior2/5

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

No annotations provided, so description carries full burden. Discloses basic return structure but lacks details on rate limits, authentication, data freshness, or any side effects. For a read-only tool, minimal transparency.

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?

Very short description, front-loaded with the action. The docstring is somewhat redundant but not excessive. Could be slightly more structured, but overall efficient.

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

Completeness3/5

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

Single parameter with straightforward functionality. Description covers input and basic output fields. However, lacks information on pagination, limits, data source, or error handling, leaving gaps for an agent.

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 has 0% description coverage for the 'domain' parameter. Description adds a brief explanation 'The domain to query', which provides minimal but necessary context beyond the schema's type-only definition.

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?

Description clearly states 'Get backlinks list for the specified domain', using a strong verb and specific resource. Sibling tools (get_traffic, keyword_difficulty, keyword_generator) cover different data, so this is well differentiated.

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 versus alternatives. Does not mention any preconditions, limitations, or when to avoid using it. Only implied by the name.

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

get_trafficA

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

A3.7/5.0

Behavior3/5

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

With no annotations, description implies a read-only operation but does not disclose side effects, auth needs, or data freshness. 'Check the estimated search traffic' is clear but lacks depth on behavior beyond the parameter list.

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, front-loaded purpose, then parameter list. No extraneous text; every sentence adds value.

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

Completeness3/5

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

Adequate for a simple tool with 3 params and no output schema, but fails to specify return data shape or error cases. Could be more complete with examples or output details.

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

Parameters4/5

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

Schema coverage is 0%, so description compensates by explaining each parameter: domain_or_url, country (with default), and mode (with enum values). Adds useful context beyond the schema.

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 the tool checks estimated search traffic for any website, which distinguishes it from siblings like get_backlinks_list 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 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 versus alternatives. Does not mention contexts, exclusions, or scenarios where other tools are better suited.

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

C2.8/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden to disclose behavioral traits beyond the input schema. It only states the basic action (get difficulty) but does not mention what the output looks like, whether it is a number or label, or any constraints like rate limits or data freshness. This is insufficient for a tool without output schema.

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?

The description is a single sentence of 8 words, extremely concise and front-loaded with the verb and object. Every word adds value, and there is no unnecessary information.

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 the tool's simplicity (2 params, no output schema, no annotations), the description should compensate by explaining the difficulty metric, return format, or common use cases. It fails to do so, leaving the agent uncertain about what the response contains and how to interpret it.

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?

The input schema has two parameters (keyword, country) with zero description coverage. The description only mentions 'the specified keyword', adding minimal meaning for that parameter. It does not explain the 'country' parameter's purpose or default behavior, nor does it provide any additional context beyond the 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 states the verb 'Get' and the resource 'keyword difficulty', clearly indicating what the tool does. It differentiates from sibling tools like get_backlinks_list and get_traffic by focusing on difficulty. However, it does not specify what the difficulty metric represents (e.g., score range), which slightly reduces clarity.

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 the sibling tools (get_backlinks_list, get_traffic, keyword_generator). There is no mention of use cases, prerequisites, or alternatives, leaving the agent without context for selection.

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

Behavior1/5

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

No annotations are provided, and the description does not disclose any behavioral traits such as result format, limits, or side effects. It adds no value beyond the basic purpose.

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?

The description is a single sentence, making it concise, but it is underspecified to the point of being unhelpful. It is front-loaded but lacks necessary detail.

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 no output schema, no annotations, and three parameters undocumented, the description is severely incomplete. It does not convey return values, usage context, or parameter 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%, yet the description fails to explain the meaning or usage of any of the three parameters (keyword, country, search_engine). It does not compensate for the lack of schema descriptions.

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?

The description clearly states the verb 'get' and the resource 'keyword ideas', and the name 'keyword_generator' aligns. It distinguishes from sibling tools (get_backlinks_list, get_traffic, keyword_difficulty) which focus on other aspects.

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 vs alternatives, nor does it mention context or exclusions. It only states what it does, leaving the agent with no directional support.

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

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0

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

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

VibeSEO
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
Metrifyr
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 9 months ago (2025-11-24 18:08 UTC)
16
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 3 months ago (2026-05-22 22:37 UTC)
13
18
5
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/iflow-mcp/egebese-seo-research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server