🎯 Competitive Intelligence MCP

Track competitors. Monitor SERP rankings. Scrape pages. Build knowledge graphs.

A production-ready Model Context Protocol (MCP) server that gives AI agents real-time competitive intelligence superpowers. Built for marketers, e-commerce teams, and growth hackers who want to automate competitor tracking at scale.

🚀 Quick Start · 📖 Documentation · 🔧 API Reference · 💡 Examples

✨ Features

| Feature | Description | Status | |---------|-------------|--------| | 🏢 Competitor Tracking | Register competitors by domain and build rich profiles | ✅ Ready | | 🔍 SERP Monitoring | Check Google rankings via scraping APIs | ✅ Ready | | 🕷️ Page Scraping | Extract content from competitor pages with bot protection bypass | ✅ Ready | | 🧠 Knowledge Graphs | Store entities and relationships per competitor (products, tech, people) | ✅ Ready | | 📈 Ranking History | Track position changes over time with trend analysis | ✅ Ready | | 📊 Competitive Reports | Generate comprehensive snapshots of your competitive landscape | ✅ Ready | | 🤖 MCP Native | Works with Claude, Cursor, Windsurf, and any MCP client | ✅ Ready | | 🔌 Programmatic API | Use as a library in your own Node.js applications | ✅ Ready | | 🖥️ CLI Tool | Command-line interface for quick operations | ✅ Ready | | 💾 Local Storage | All data stored locally in JSON — no cloud required | ✅ Ready |

🚀 Quick Start

Installation

# Global install (recommended for CLI usage)
npm install -g competitive-intel-mcp

# Or use npx directly
npx competitive-intel-mcp <command>

As an MCP Server

Add to your Claude Desktop, Cursor, Windsurf, or any MCP client:

{
  "mcpServers": {
    "competitive-intel": {
      "command": "npx",
      "args": ["competitive-intel-mcp", "server"]
    }
  }
}

That's it. Your AI assistant now has 13 competitive intelligence tools available.

CLI Usage

# Add your first competitor
competitive-intel-mcp add-competitor -n "Shopify" -d shopify.com --notes "E-commerce platform leader"

# Track a keyword
competitive-intel-mcp add-topic -k "best ecommerce platform"

# Check live SERP rankings
competitive-intel-mcp check-serp -k "best ecommerce platform" --depth 10

# Generate a full report
competitive-intel-mcp report

Programmatic API

import { GraphStore, SerpEngine, Scraper, createServer } from 'competitive-intel-mcp';

// Track competitors
const store = new GraphStore();
const competitor = store.addCompetitor('Shopify', 'shopify.com', 'E-commerce platform');

// Check SERP rankings
const serp = new SerpEngine();
const results = await serp.checkSerp('best ecommerce platform', 10);

// Scrape competitor pages
const scraper = new Scraper();
const page = await scraper.scrapePage('https://shopify.com/pricing');

// Build knowledge graph
store.storeEntities(competitor.id, [
  { name: 'Shopify Plus', type: 'product' },
  { name: 'Ruby on Rails', type: 'technology' },
]);

store.linkEntities(competitor.id, [
  { source: 'Shopify Plus', target: 'Ruby on Rails', type: 'built_on' },
]);

// Start MCP server
await createServer();

🔧 Configuration

Configuration

Add your credentials directly in your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "competitive-intel": {
      "command": "npx",
      "args": ["-y", "competitive-intel-mcp"],
      "env": {
        "BRIGHTDATA_API_KEY": "your-api-key",
        "BRIGHTDATA_GEO_LOCATION": "us"
      }
    }
  }
}

| Variable | Description | |----------|-------------| | BRIGHTDATA_API_KEY | Bright Data API key for live SERP and scraping | | BRIGHTDATA_GEO_LOCATION | Geo for SERP results (default: us) |

Note: Without an API key the server runs in demo mode with simulated results — useful for testing.

Data Storage

All data is stored locally in:

~/.competitive-intel-mcp/store.json

No cloud, no database, no dependencies. Your competitive intelligence stays on your machine.

📖 Documentation

Available MCP Tools

When connected to an MCP client, these tools become available to your AI assistant:

Competitor Management

| Tool | Description | |------|-------------| | competitive-intel_add_competitor | Register a new competitor to track | | competitive-intel_list_competitors | List all tracked competitors |

Topic & Keyword Tracking

| Tool | Description | |------|-------------| | competitive-intel_add_topic | Add a keyword/topic to monitor in SERP | | competitive-intel_list_topics | List all tracked keywords |

SERP & Scraping

| Tool | Description | |------|-------------| | competitive-intel_check_serp | Fetch live Google SERP rankings for a keyword | | competitive-intel_scrape_page | Scrape a competitor page for content extraction |

Knowledge Graph

| Tool | Description | |------|-------------| | competitive-intel_store_entities | Store extracted entities (products, tech, people, etc.) | | competitive-intel_link_entities | Create relationships between entities | | competitive-intel_query_graph | Search the competitive intelligence graph | | competitive-intel_entity_neighbors | Get all entities connected to a given entity |

Analytics & Reporting

| Tool | Description | |------|-------------| | competitive-intel_ranking_history | Get historical ranking data for a competitor | | competitive-intel_recent_changes | Get recent ranking changes across all competitors | | competitive-intel_competitive_report | Generate a comprehensive competitive snapshot |

💡 Examples

Example 1: Track a New Competitor

competitive-intel-mcp add-competitor \
  -n "BigCommerce" \
  -d bigcommerce.com \
  --notes "E-commerce platform competitor, strong B2B features"

Example 2: Monitor SERP for Multiple Keywords

# Add keywords
competitive-intel-mcp add-topic -k "best ecommerce platform"
competitive-intel-mcp add-topic -k "online store builder"
competitive-intel-mcp add-topic -k "dropshipping tools"

# Check rankings
competitive-intel-mcp check-serp -k "best ecommerce platform" --depth 20
competitive-intel-mcp check-serp -k "online store builder" --depth 20

Example 3: Build a Knowledge Graph

After scraping a competitor's page, store what you learned:

# First, scrape the page
competitive-intel-mcp scrape -u https://example-competitor.com/products

# Then add the competitor
competitive-intel-mcp add-competitor -n "Example Store" -d example-competitor.com

# Store entities (via MCP tool or programmatic API)

Example 4: Weekly Competitive Report

# Run this every Monday
competitive-intel-mcp check-serp -k "best ecommerce platform"
competitive-intel-mcp check-serp -k "online store builder"
competitive-intel-mcp check-serp -k "dropshipping tools"

# Generate report
competitive-intel-mcp report

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                    MCP Client (Claude/Cursor)               │
└──────────────────────┬──────────────────────────────────────┘
                       │ stdio
┌──────────────────────▼──────────────────────────────────────┐
│              competitive-intel-mcp Server                   │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────────────┐ │
│  │  GraphStore │  │ SerpEngine  │  │      Scraper        │ │
│  │  (JSON)     │  │ (API/Demo)  │  │  (API/Demo)         │ │
│  │             │  │             │  │                     │ │
│  └─────────────┘  └─────────────┘  └─────────────────────┘ │
└─────────────────────────────────────────────────────────────┘

Tech Stack:

• Runtime: Node.js 18+
• Language: TypeScript 5.0+
• Protocol: Model Context Protocol (MCP) SDK
• Storage: Local JSON files
• APIs: Optional external scraping APIs

🧪 Development

# Clone the repo
git clone https://github.com/danishashko/competitive-intel-mcp.git
cd competitive-intel-mcp

# Install dependencies
npm install

# Build
npm run build

# Dev mode (watch)
npm run dev

# Test CLI
npm test

🗺️ Roadmap

• [x] Core MCP server with 13 tools
• [x] CLI interface
• [x] Programmatic API
• [x] External API integration
• [x] Local JSON storage
• [ ] SQLite backend option
• [ ] Scheduled monitoring (cron)
• [ ] Slack/Discord alerts for ranking changes
• [ ] Export to CSV/JSON
• [ ] Web dashboard
• [ ] Multi-location SERP tracking
• [ ] Mobile vs desktop rankings

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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

Please make sure to update tests as appropriate.

📄 License

This project is licensed under the MIT License — see the LICENSE file for details.

By Daniel Shashko

Made with ❤️ by Daniel Shashko