Serper Search MCP

io.github.smjahid012/serper-search-mcp

Universal Google Search MCP: web, images, places, shopping, scholar, patents, deep research & RAG

View repository →Homepage →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "serper-search-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "serper-search-mcp@4.0.1"
      ],
      "env": {
        "SERPER_API_KEY": "<your SERPER_API_KEY>",
        "GEMINI_API_KEY": "<your GEMINI_API_KEY>",
        "OPENROUTER_API_KEY": "<your OPENROUTER_API_KEY>",
        "TAVILY_API_KEY": "<your TAVILY_API_KEY>",
        "BRAVE_API_KEY": "<your BRAVE_API_KEY>",
        "EXA_API_KEY": "<your EXA_API_KEY>",
        "FIRECRAWL_API_KEY": "<your FIRECRAWL_API_KEY>"
      }
    }
  }
}
Environment variables
  • SERPER_API_KEYrequiredsecretYour Serper API key — get 2,500 free credits at https://serper.dev
  • GEMINI_API_KEYsecretGoogle AI Studio key for deep_research (free tier) — get one at https://ai.google.dev
  • OPENROUTER_API_KEYsecretOpenRouter LLM key for deep_research — takes priority over Gemini; free models at https://openrouter.ai
  • TAVILY_API_KEYsecretTavily fallback search provider — 1,000 free searches/month at https://tavily.com
  • BRAVE_API_KEYsecretBrave Search fallback provider — 2,000 free queries/month at https://brave.com/search/api
  • EXA_API_KEYsecretExa neural semantic search fallback — get a key at https://exa.ai
  • FIRECRAWL_API_KEYsecretFirecrawl for JS-rendered page scraping (upgrades the scrape tool) — https://firecrawl.dev

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
4.0.1
Registry
active
Published
11/9/2026

More Search & Web servers

Browse all Search & Web →

YeetIt

snappyio

Instant web publishing for AI agents. POST HTML, get a live URL. No account needed.

Search & WebAdded Feb 2026

Deepcrawl

Soflutionltd

Clone websites, scrape pages to markdown and crawl whole sites. A free Firecrawl alternative.

Search & WebAdded 2 weeks ago

Flintrail

Soflutionltd

Drive a real Chrome live, record a flow once, replay it in milliseconds without an LLM.

Search & WebAdded 2 weeks ago

Openunfurl

SolvoHQ

Zero-signup anonymous link-unfurl API. One GET returns clean JSON metadata for any public URL.

Search & WebAdded May 2026

find-my-session

SomeNoneAI

Read-only session finder across coding-agent harnesses: search, page prompts, hand off.

Search & WebAdded 2 days ago

Google Search Console MCP

sonnivasquez

Local, read-only Google Search Console MCP server. Quick Connect needs no Cloud project.

Search & WebAdded 1 week ago

Add the badge to your site

Show visitors that Serper Search MCP is listed here — it’s also the link we check for a free listing.

Serper Search MCP — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-smjahid012-serper-search-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Serper Search MCP — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Serper Search MCP — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-smjahid012-serper-search-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.