SEO Insights MCP Server

This project provides a Model Context Protocol (MCP) server that connects AI assistants to SEO APIs for backlinks analysis, keyword research, and traffic analysis.

• Github
• npm

Disclaimer

This project is not affiliated with any of the APIs used in this project. You will need a CAPSOLVER API key to resolve Ahrefs captchas.

Available Features

SEO Tools

• [x] Get backlinks list for any domain
• [x] Generate keyword ideas for any seed keyword
• [x] Check keyword difficulty and SERP analysis
• [x] Analyze website traffic and top performing content

Supported Transports

• [x] "stdio" transport - Default transport for CLI usage
• [x] "Streamable HTTP" transport - For web-based clients
  • [ ] Implement auth ("Authorization" headers with Bearer <token>)
• [x] ~~"sse" transport~~ (Deprecated)
• [ ] Write tests

How to use

CLI

# Analyze website traffic
npm run dev:cli -- get-traffic --domain "example.com"
# Equivalent to
npm run dev:cli -- get-traffic --domain "example.com" --mode "subdomains"

# Analyze website traffic for a specific country
npm run dev:cli -- get-traffic --domain "example.com" --mode "exact" --country "uk"

# Get backlinks for a domain
npm run dev:cli -- get-backlinks --domain "example.com"

# Generate keyword ideas
npm run dev:cli -- keyword-generator --keyword "seo tools" --country "us"

# Generate keyword ideas with specific search engine
npm run dev:cli -- keyword-generator --keyword "seo tools" --country "us" --search-engine "Google"

# Check keyword difficulty
npm run dev:cli -- keyword-difficulty --keyword "seo analytics" --country "us"

MCP Setup

For local configuration with stdio transport:

{
  "mcpServers": {
    "seo-insights": {
      "command": "node",
      "args": ["/path/to/seo-insights-mcp-server/dist/index.js"],
      "transportType": "stdio"
    }
  }
}

For remote HTTP configuration:

{
  "mcpServers": {
    "seo-insights": {
      "type": "http",
      "url": "http://localhost:8080/mcp"
    }
  }
}

Environment Variables for HTTP Transport:

You can configure the HTTP server using these environment variables:

• MCP_HTTP_HOST: The host to bind to (default: 127.0.0.1)
• MCP_HTTP_PORT: The port to listen on (default: 8080)
• MCP_HTTP_PATH: The endpoint path (default: /mcp)

Source Code Overview

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI systems to securely and contextually connect with external tools and data sources.

This boilerplate implements the MCP specification with a clean, layered architecture that can be extended to build custom MCP servers for any API or data source.

Why Use This Boilerplate?

• Production-Ready Architecture: Follows the same pattern used in published MCP servers, with clear separation between CLI, tools, controllers, and services.

• Type Safety: Built with TypeScript for improved developer experience, code quality, and maintainability.

• Working Example: Includes a fully implemented IP lookup tool demonstrating the complete pattern from CLI to API integration.

• Testing Framework: Comes with testing infrastructure for both unit and CLI integration tests, including coverage reporting.

• Development Tooling: Includes ESLint, Prettier, TypeScript, and other quality tools preconfigured for MCP server development.

Getting Started

Prerequisites

• Node.js (>=18.x): Download
• Git: For version control

... View full README on GitHub