FetchSERP
About
All-in-One SEO & Web Intelligence Toolkit API [FetchSERP](https://www.fetchserp.com)
Explore
- Domain analysis: backlinks, DNS, WHOIS, SSL, tech stack
- Keyword research: search volume, suggestions, long-tail generation
- SERP retrieval from Google, Bing, Yahoo, DuckDuckGo
- AI-powered webpage analysis with custom prompts
- Web scraping with and without JavaScript, plus proxy support
- User management: check API credits and account info
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
FetchSERPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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!
docker run -i --rm \
-e FETCHSERP_API_TOKEN="your_token_here" \
ghcr.io/fetchserp/fetchserp-mcp-server-node:latest
docker build --platform=linux/amd64 -t olivier86/fetchserp-mcp-server-node:latest --push .
docker run -p 8000:8000 olivier86/fetchserp-mcp-server-node:latest
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"fetchserp": {
"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"
}
}
}
}
}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"
}
}
}A Model Context Protocol (MCP) server that exposes the FetchSERP API for SEO, SERP analysis, web scraping, and keyword research.
Features
This MCP server provides access to all FetchSERP API endpoints:
SEO & Analysis
- Domain Analysis: Get backlinks, domain info (DNS, WHOIS, SSL, tech stack) - Keyword Research: Search volume, suggestions, long-tail keyword generation - SEO Analysis: Comprehensive webpage SEO analysis - AI Analysis: AI-powered webpage analysis with custom prompts - Moz Integration: Domain authority and Moz metricsSERP & Search
- Search Results: Get SERP results from Google, Bing, Yahoo, DuckDuckGo - AI Overview: Google's AI overview with JavaScript rendering - Enhanced Results: SERP with HTML or text content - Ranking Check: Domain ranking for specific keywords - Indexation Check: Verify if pages are indexedWeb Scraping
- Basic Scraping: Scrape webpages without JavaScript - JS Scraping: Execute custom JavaScript on pages - Proxy Scraping: Scrape with country-specific proxies - Domain Scraping: Scrape multiple pages from a domainUser Management
- Account Info: Check API credits and user informationInstallation
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
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
Option 1: Using npx (Local/Remote GitHub)
Add this server to your MCP client configuration. For example, in Claude Desktop:
{
"mcpServers": {
"fetchserp": {
"command": "npx",
"args": [
"github:fetchSERP/fetchserp-mcp-server-node"
],
"env": {
"FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
}
}
}
}
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:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
