Skip to main content

MCP server for tracking brand visibility in LLMs (ChatGPT, Claude, Gemini, Perplexity) using DataForSEO API

Project description

DataForSEO AI Optimization MCP Server

Complete MCP server for tracking brand visibility in LLMs (ChatGPT, Claude, Gemini, Perplexity).

🚀 Features

Tier 1: Core Tools (Solve 80% of demand)

  • search_mentions - Find brand mentions across all LLMs
  • ai_keyword_search_volume - Get AI-specific search volume
  • chatgpt_live - Query ChatGPT with citations
  • claude_live - Query Claude with citations
  • gemini_live - Query Gemini with citations

Tier 2: High-Value Tools

  • top_domains - Competitor analysis
  • aggregated_metrics - Historical tracking
  • perplexity_live - Complete LLM coverage
  • chatgpt_scraper_live - Deep HTML extraction
  • cross_aggregated_metrics - Multi-domain comparison

Tier 3: Power Features

  • top_pages - Content optimization insights
  • list_chatgpt_models - Available ChatGPT models
  • list_claude_models - Available Claude models
  • list_gemini_models - Available Gemini models
  • list_perplexity_models - Available Perplexity models

Tier 4: Batch Operations

  • chatgpt_task_post/ready/get - Bulk ChatGPT queries
  • claude_task_post/ready/get - Bulk Claude queries

Total: 21 production-ready tools

📋 Prerequisites

  • Python 3.10+
  • DataForSEO account with API credentials
  • Claude Desktop (for testing)

🔧 Installation

Step 1: Clone or Create Directory

mkdir dataforseo-mcp-server
cd dataforseo-mcp-server

Step 2: Create Virtual Environment

macOS/Linux:

python3 -m venv venv
source venv/bin/activate

Windows:

python -m venv venv
venv\Scripts\activate

Step 3: Install Dependencies

pip install -r requirements.txt

Step 4: Configure Credentials

  1. Copy .env.example to .env:
cp .env.example .env
  1. Edit .env and add your DataForSEO credentials:
DATAFORSEO_LOGIN=your_email@example.com
DATAFORSEO_PASSWORD=your_api_password_here

Get credentials from: https://app.dataforseo.com/api-dashboard

Step 5: Test Authentication

python test_auth.py

Expected output:

✅ SUCCESS! Your DataForSEO credentials are working!

🚀 Running the Server

Test Locally

python server.py

Configure Claude Desktop

macOS:

Edit: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "dataforseo-ai": {
      "command": "/FULL/PATH/TO/venv/bin/python",
      "args": ["/FULL/PATH/TO/server.py"],
      "env": {
        "DATAFORSEO_LOGIN": "your_email@example.com",
        "DATAFORSEO_PASSWORD": "your_api_password"
      }
    }
  }
}

Windows:

Edit: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "dataforseo-ai": {
      "command": "C:\\FULL\\PATH\\TO\\venv\\Scripts\\python.exe",
      "args": ["C:\\FULL\\PATH\\TO\\server.py"],
      "env": {
        "DATAFORSEO_LOGIN": "your_email@example.com",
        "DATAFORSEO_PASSWORD": "your_api_password"
      }
    }
  }
}

Get full paths:

# macOS/Linux
pwd  # Current directory
which python  # Python path (use venv/bin/python)

# Windows
cd  # Current directory
where python  # Python path (use venv\Scripts\python.exe)

Restart Claude Desktop

  1. Quit Claude Desktop completely
  2. Reopen Claude Desktop
  3. Look for 🔌 icon in bottom-right
  4. Click it - you should see "dataforseo-ai" listed

📖 Usage Examples

Example 1: Check Brand Mentions

Use search_mentions to check if "Semrush" is mentioned in LLMs

Example 2: Get AI Search Volume

Get AI search volume for: "SEO tools", "keyword research", "link building"

Example 3: Multi-LLM Comparison

Compare responses: Ask ChatGPT, Claude, and Gemini "What are the best SEO tools?"

Example 4: Competitor Analysis

Use top_domains to see which competitors dominate for "project management software"

Example 5: Historical Tracking

Use aggregated_metrics to track semrush.com mentions from 2025-01-01 to 2025-03-01

💰 Cost Tracking

All tools log their credit costs:

  • search_mentions: 2 credits ($0.002)
  • ai_keyword_search_volume: 1 credit per keyword ($0.001)
  • chatgpt_live: 5-20 credits depending on model ($0.005-$0.020)
  • top_domains: 2 credits ($0.002)
  • aggregated_metrics: 2 credits ($0.002)
  • Model listings: FREE (0 credits)

🐛 Troubleshooting

Error: "DATAFORSEO_LOGIN and DATAFORSEO_PASSWORD must be set"

  • Check .env file exists
  • Verify credentials are correct
  • No extra spaces around = signs

Error: "API Error: Authentication failed"

Error: "ModuleNotFoundError: No module named 'fastmcp'"

  • Activate virtual environment: source venv/bin/activate
  • Reinstall dependencies: pip install -r requirements.txt

Claude Desktop doesn't show the server

  • Check config file path is correct
  • Use absolute paths (not relative paths like ~/)
  • Restart Claude Desktop completely
  • Check logs in Claude Desktop settings

📊 Logging

All tools log:

  • Input parameters
  • Output summaries
  • Credit costs
  • Timestamps

Check terminal output when server runs for detailed logs.

🔐 Security

  • Never commit .env to git
  • .gitignore is pre-configured
  • Credentials are loaded from environment variables only

📚 API Documentation

Full DataForSEO API docs: https://docs.dataforseo.com/v3/ai_optimization/overview/

🆘 Support

Issues? Check:

  1. DataForSEO API status: https://status.dataforseo.com/
  2. DataForSEO support: https://dataforseo.com/support
  3. Your account credits: https://app.dataforseo.com/

📝 License

MIT License - Use freely in your projects

🎯 What Problems This Solves

  1. Brand Invisibility - 43.4% of queries get zero mentions
  2. Unknown AI Search Volume - Traditional volume doesn't translate
  3. Multi-LLM Chaos - Different responses across LLMs
  4. Competitor Blind Spots - Can't measure Share of Voice
  5. Citation Paradox - High mentions ≠ website traffic

Built based on real market demand from SEO communities.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dataforseo_mcp_server-1.0.0.tar.gz (13.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dataforseo_mcp_server-1.0.0-py3-none-any.whl (12.0 kB view details)

Uploaded Python 3

File details

Details for the file dataforseo_mcp_server-1.0.0.tar.gz.

File metadata

  • Download URL: dataforseo_mcp_server-1.0.0.tar.gz
  • Upload date:
  • Size: 13.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for dataforseo_mcp_server-1.0.0.tar.gz
Algorithm Hash digest
SHA256 767d2840423883326019bf1ee123fdc2256f63e72fa131f2ee49d90b9d57bb47
MD5 8037ec024a5450ed4b7ab6e5166e831c
BLAKE2b-256 5a6df5d773d33788ad84cc3136d01946e4b2997f56e850eb3a05aaae9ac20fe1

See more details on using hashes here.

File details

Details for the file dataforseo_mcp_server-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for dataforseo_mcp_server-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6709c0437f905dfbb4a7ebe515aa98fa98809999b8fb91e8a5c5634e92d95a33
MD5 f753bffe04d52664eca227940138341c
BLAKE2b-256 708c025e07738ebaa566afbd8b627beea485f67ea9bae6dde703bd8b6eb0faf2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page