The ReviewWebsite.com MCP server connects AI assistants to the ReviewWebsite.com API, enabling website review management, URL to markdown conversion, data extraction, and SEO analysis capabilities through the Model Context Protocol (MCP).
To install and configure the ReviewWebsite MCP server:
# Clone the repository
git clone https://github.com/mrgoonie/reviewwebsite-mcp-server.git
cd reviewwebsite-mcp-server
# Install dependencies
npm install
You can run the server in development mode with:
# Using stdio transport (default)
npm run dev:server
# Using HTTP transport
npm run dev:server:http
When using HTTP transport, the server will be available at http://127.0.0.1:8080/mcp by default.
The server provides a command-line interface for accessing ReviewWebsite.com functionality:
# Create a new review
npm run dev:cli -- create-review --url "https://example.com" --instructions "Review this website" --api-key "your-api-key"
# Get a specific review by ID
npm run dev:cli -- get-review --review-id "review-id" --api-key "your-api-key"
# List all reviews
npm run dev:cli -- list-reviews --page 1 --limit 10 --api-key "your-api-key"
# Update a review
npm run dev:cli -- update-review --review-id "review-id" --url "https://example.com" --instructions "Updated instructions" --api-key "your-api-key"
# Delete a review
npm run dev:cli -- delete-review --review-id "review-id" --api-key "your-api-key"
# Convert URL to Markdown
npm run dev:cli -- convert-to-markdown --url "https://example.com" --model "gpt-4o" --api-key "your-api-key"
# Extract structured data from URL
npm run dev:cli -- extract-data --url "https://example.com" --instructions "Extract product information" --api-key "your-api-key"
# Scrape URL
npm run dev:cli -- scrape-url --url "https://example.com" --api-key "your-api-key"
# Extract links from URL
npm run dev:cli -- extract-links --url "https://example.com" --type "all" --api-key "your-api-key"
# Summarize URL
npm run dev:cli -- summarize-url --url "https://example.com" --model "gpt-4o" --api-key "your-api-key"
# Get keyword ideas for SEO
npm run dev:cli -- seo-keyword-ideas --keyword "digital marketing" --country "us" --search-engine "Google" --api-key "your-api-key"
# Check keyword difficulty
npm run dev:cli -- seo-keyword-difficulty --keyword "digital marketing" --country "us" --api-key "your-api-key"
# Analyze website traffic
npm run dev:cli -- seo-traffic --domain-or-url "example.com" --mode "subdomains" --country "us" --api-key "your-api-key"
# Get backlinks for a domain
npm run dev:cli -- seo-backlinks --domain "example.com" --api-key "your-api-key"
To integrate the ReviewWebsite MCP server with AI assistants, you'll need to configure it in your MCP configuration.
{
"mcpServers": {
"reviewwebsite": {
"command": "node",
"args": ["/path/to/reviewwebsite-mcp-server/dist/index.js"],
"transportType": "stdio"
}
}
}
{
"mcpServers": {
"reviewwebsite": {
"type": "http",
"url": "http://localhost:8080/mcp"
}
}
}
Configure the HTTP server with 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)You can store your API key in the MCP configuration file:
{
"reviewwebsite": {
"environments": {
"DEBUG": "true",
"REVIEWWEBSITE_API_KEY": "your-api-key-here"
}
}
}
If you wish to enable debug logs for development:
# Set environment variable
DEBUG=true npm run dev:server
You can also access the visual MCP Inspector to test your tools and view request/response details by running the development server and opening http://localhost:5173 in your browser.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "reviewwebsite" '{"command":"node","args":["/path/to/reviewwebsite-mcp-server/dist/index.js"],"transportType":"stdio"}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"reviewwebsite": {
"command": "node",
"args": [
"/path/to/reviewwebsite-mcp-server/dist/index.js"
],
"transportType": "stdio"
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"reviewwebsite": {
"command": "node",
"args": [
"/path/to/reviewwebsite-mcp-server/dist/index.js"
],
"transportType": "stdio"
}
}
}3. Restart Claude Desktop for the changes to take effect