Fetchserp MCP Server Node

🚀 FetchSERP MCP Server

A Model Context Protocol (MCP) server that exposes the FetchSERP API for SEO, SERP analysis, web scraping, and keyword research.

🚀 Quick Start

This MCP server allows you to access the FetchSERP API directly. No installation is required as it runs directly from GitHub using npx. You just need to obtain your FetchSERP API token by signing up at https://www.fetchserp.com. New users get 250 free credits to start.

✨ Features

This MCP server provides access to all FetchSERP API endpoints:

SEO & Analysis

• Domain Analysis: Retrieve backlinks and comprehensive domain information, including DNS, WHOIS, SSL, and tech stack.
• Keyword Research: Obtain search volume, suggestions, and generate long - tail keywords.
• SEO Analysis: Conduct a comprehensive SEO analysis of webpages.
• AI Analysis: Perform AI - powered webpage analysis with custom prompts.
• Moz Integration: Get domain authority and Moz metrics.

SERP & Search

• Search Results: Fetch SERP results from Google, Bing, Yahoo, DuckDuckGo.
• AI Overview: Get Google's AI overview with JavaScript rendering.
• Enhanced Results: Retrieve SERP with HTML or text content.
• Ranking Check: Check the domain ranking for specific keywords.
• Indexation Check: Verify if pages are indexed.

Web Scraping

• Basic Scraping: Scrape webpages without JavaScript.
• JS Scraping: Execute custom JavaScript on pages.
• Proxy Scraping: Scrape using country - specific proxies.
• Domain Scraping: Scrape multiple pages from a domain.

User Management

• Account Info: Check API credits and user information.

📦 Installation

No installation required! This MCP server runs directly from GitHub using npx.

Get your FetchSERP API token: Sign up at https://www.fetchserp.com to get your API token. New users get 250 free credits to get started!

💻 Usage Examples

Transport Modes

This MCP server supports two transport modes:

npx mode (Option 1):

• ✅ Zero installation required
• ✅ Always gets latest version from GitHub
• ✅ Perfect for individual users
• ✅ Runs locally with Claude Desktop

HTTP mode (Option 2):

• ✅ Remote deployment capability
• ✅ Multiple clients can connect
• ✅ Better for enterprise/team environments
• ✅ Centralized server management
• ✅ Single API key authentication (FetchSERP token)
• ✅ Scalable architecture

Configuration

Basic Usage

Option 1: Using npx (Local/Remote GitHub) Add this server to your MCP client configuration. For example, in Claude Desktop using github registry:

{
  "mcpServers": {
    "fetchserp": {
      "command": "npx",
      "args": [
        "github:fetchSERP/fetchserp-mcp-server-node"
      ],
      "env": {
        "FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
      }
    }
  }
}

or using npm registry

{
  "mcpServers": {
    "fetchserp": {
      "command": "npx",
      "args": ["fetchserp-mcp-server"],
      "env": {
        "FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
      }
    }
  }
}

Advanced Usage

Option 2: Claude API with MCP Server For programmatic usage with Claude's API and your deployed MCP server:

const claudeRequest = {
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  messages: [
    {
      role: "user", 
      content: question
    }
  ],
  // MCP Server Configuration
  mcp_servers: [
    {
      type: "url",
      url: "https://mcp.fetchserp.com/sse",
      name: "fetchserp",
      authorization_token: FETCHSERP_API_TOKEN,
      tool_configuration: {
        enabled: true
      }
    }
  ]
};

const response = await httpRequest('https://api.anthropic.com/v1/messages', {
  method: 'POST',
  headers: {
    'x-api-key': CLAUDE_API_KEY,
    'anthropic-version': '2023-06-01',
    'anthropic-beta': 'mcp-client-2025-04-04',
    'content-type': 'application/json'
  }
}, JSON.stringify(claudeRequest));

Option 3: OpenAI API with MCP Server For programmatic usage with OpenAI's API and your deployed MCP server:

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const res = await openai.responses.create({
  model: "gpt-4.1",
  tools: [
    {
      type: "mcp",
      server_label: "fetchserp",
      server_url: "https://mcp.fetchserp.com/sse",
      headers: {
        Authorization: `Bearer ${FETCHSERP_API_TOKEN}`
      }
    }
  ],
  input: question
});

console.log(res.choices[0].message);

Option 4: Docker Use the pre - built Docker image from GitHub Container Registry for containerized deployment:

{
  "mcpServers": {
    "fetchserp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "FETCHSERP_API_TOKEN",
        "ghcr.io/fetchserp/fetchserp-mcp-server-node:latest"
      ],
      "env": {
        "FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
      }
    }
  }
}

Docker Features:

• ✅ Containerized deployment
• ✅ Cross - platform compatibility (ARM64 & AMD64)
• ✅ Isolated environment
• ✅ Easy scaling and deployment
• ✅ Automated builds from GitHub

Manual Docker Usage:

# Pull the latest image
docker pull ghcr.io/fetchserp/fetchserp-mcp-server-node:latest

# Run with environment variable
docker run -i --rm \
  -e FETCHSERP_API_TOKEN="your_token_here" \
  ghcr.io/fetchserp/fetchserp-mcp-server-node:latest

# Or run in HTTP mode on port 8000
docker run -p 8000:8000 \
  -e FETCHSERP_API_TOKEN="your_token_here" \
  -e MCP_HTTP_MODE=true \
  ghcr.io/fetchserp/fetchserp-mcp-server-node:latest

📚 Documentation

Available Tools

Domain & SEO Analysis

Keyword Research

SERP & Search

Web Scraping

User Management

API Token

You need a FetchSERP API token to use this server.

Getting your API token:

1. Sign up at https://www.fetchserp.com
2. New users automatically receive 250 free credits to get started
3. Your API token will be available in your dashboard

Set the token as an environment variable:

export FETCHSERP_API_TOKEN="your_token_here"

Error Handling

The server includes comprehensive error handling:

• Missing API token validation
• API response error handling
• Input validation
• Proper MCP error responses

Docker deploy

docker build --platform=linux/amd64 -t olivier86/fetchserp-mcp-server-node:latest --push .
docker build --platform=linux/amd64 -t ghcr.io/fetchserp/mcp-server-node:latest --push .

docker run -p 8000:8000 olivier86/fetchserp-mcp-server-node:latest

To start tunneling

nohup ngrok http 8000 --domain guinea-dominant-jolly.ngrok-free.app > /var/log/ngrok.log 2>&1 &

npm login
npm publish --access public