Welcome to the fetchSERP API! This quick-start guide walks you through every way you can call our endpoints—cURL, official SDKs, and LLM integrations—so you can be productive right away.

​
1. Get your API token

  1. Sign up or log in at www.fetchserp.com
  2. Copy your API token from the dashboard
  3. Save it as an environment variable (recommended):
export FETCHSERP_API_TOKEN="YOUR_API_TOKEN"

​
2. Your first request (cURL)

curl -X GET "https://www.fetchserp.com/api/v1/serp" \ 
  -G \
  -d "search_engine=google" \
  -d "country=us" \
  -d "pages_number=1" \
  -d "query=serp+api" \
  -H "accept: application/json" \
  -H "authorization: Bearer $FETCHSERP_API_TOKEN"
You should receive a 200 OK response with structured search results.

​
3. Use the official SDKs

​
JavaScript / TypeScript

npm install fetchserp

import FetchSERP from 'fetchserp';

const client = new FetchSERP(process.env.FETCHSERP_API_TOKEN);
const results = await client.serp({
  query: 'serp api',
  search_engine: 'google',
  country: 'us',
  pages_number: 1
});
console.log(results.data);

​
Python

pip install fetchserp

from fetchserp import FetchSERP

client = FetchSERP()
client.api_key = os.environ['FETCHSERP_API_TOKEN']
results = client.serp(query="serp api", search_engine="google", country="us", pages_number=1)
print(results["data"])

​
Ruby

gem install fetchserp

require 'fetchserp'

client = FetchSERP::Client.new(api_key: ENV['FETCHSERP_API_TOKEN'])
results = client.serp(query: 'serp api', search_engine: 'google', country: 'us', pages_number: 1)
puts results['data']

​
4. Integrate with LLMs via MCP

fetchSERP offers a Model Context Protocol server so you can give LLMs direct access to real-time SEO data.

​
Claude API Example

const claudeRequest = {
  model: 'claude-sonnet-4-20250514',
  messages: [{ role: 'user', content: 'Show me the top keywords for fetchserp.com' }],
  mcp_servers: [
    {
      type: 'url',
      url: 'https://www.fetchserp.com/mcp',
      name: 'fetchserp',
      authorization_token: process.env.FETCHSERP_API_TOKEN,
      tool_configuration: { enabled: true }
    }
  ]
};

​
OpenAI API Example

let response = await openai.responses.create({
  model: 'gpt-4o',
  tools: [
    {
      type: 'mcp',
      server_label: 'fetchserp',
      server_url: process.env.MCP_SERVER_URL,
      headers: {
        Authorization: `Bearer ${process.env.FETCHSERP_API_TOKEN}`
      }
    }
  ],
  input: 'Find low-competition keywords for "seo api"'
});

​
Next steps

  • Explore the Endpoints for full parameter details
  • Check out real-world Use Cases
  • Read about Pricing and start with 250 free credits
Happy querying! 😎