The FetchSERP MCP Server provides access to FetchSERP's API for SEO analysis, SERP data, web scraping, and keyword research through the Model Context Protocol (MCP). This server allows AI assistants like Claude to retrieve real-time web data for more accurate and up-to-date responses.
Before using the FetchSERP MCP Server, you'll need:
To get your API token:
The server supports two main transport modes:
No installation is required as the server runs directly from GitHub using npx.
Add this server to your MCP client configuration in Claude Desktop:
{
"mcpServers": {
"fetchserp": {
"command": "npx",
"args": [
"github:fetchSERP/fetchserp-mcp-server-node"
],
"env": {
"FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
}
}
}
}
Alternatively, using npm registry:
{
"mcpServers": {
"fetchserp": {
"command": "npx",
"args": ["fetchserp-mcp-server"],
"env": {
"FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
}
}
}
}
Use the pre-built Docker image 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"
}
}
}
}
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
For programmatic usage with Claude's API:
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));
For programmatic usage with OpenAI's API:
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);
get_backlinks
Get backlinks for a domain
get_domain_info
Get comprehensive domain information
get_domain_emails
Extract emails from a domain
get_webpage_seo_analysis
Comprehensive SEO analysis of a webpage
get_webpage_ai_analysis
AI-powered webpage analysis
get_moz_analysis
Get Moz domain authority and metrics
get_keywords_search_volume
Get search volume for keywords
get_keywords_suggestions
Get keyword suggestions
get_long_tail_keywords
Generate long-tail keywords
get_serp_results
Get search engine results
check_page_indexation
Check if domain is indexed for keyword
get_domain_ranking
Get domain ranking for keyword
scrape_webpage
Scrape webpage without JavaScript
scrape_domain
Scrape multiple pages from domain
scrape_webpage_js
Scrape webpage with custom JavaScript
scrape_webpage_js_proxy
Scrape webpage with JavaScript and proxy
get_user_info
Get user information and API credits
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "fetchserp" '{"command":"npx","args":["github:fetchSERP/fetchserp-mcp-server-node"],"env":{"FETCHSERP_API_TOKEN":"your_fetchserp_api_token_here"}}'
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": {
"fetchserp": {
"command": "npx",
"args": [
"github:fetchSERP/fetchserp-mcp-server-node"
],
"env": {
"FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
}
}
}
}
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.json
2. Add this to your configuration file:
{
"mcpServers": {
"fetchserp": {
"command": "npx",
"args": [
"github:fetchSERP/fetchserp-mcp-server-node"
],
"env": {
"FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here"
}
}
}
}
3. Restart Claude Desktop for the changes to take effect