serpjet-mcp

Name: serpjet-mcp
Author: serpjet.io

Local

serpjet.ioSearch0Updated 16w ago

Repository Visit website

About serpjet-mcp

serpjet-mcp connects AI agents to SERPJET's Google SERP API, returning structured results for ten search types. It supports country and language parameters, including shopping results with prices.

Key features

01Search across ten Google result types
02Return structured SERPJET JSON
03Target results by country
04Set result language
05Retrieve shopping prices

Use cases

01Compare current shopping offers
02Search images, video, or news
03Find location-based results
04Look up scholarly works or patents

MCP support

Exposes the `google_search` tool to MCP clients. The tool accepts a query, result type, country and language settings, and pagination options.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "io-serpjet-serpjet": {
      "command": "npx",
      "args": [
        "-y",
        "serpjet-mcp"
      ],
      "env": {
        "SERPJET_API_KEY": "<SERPJET_API_KEY>"
      }
    }
  }
}

Run commandnpx -y serpjet-mcp

Environment variables to set

SERPJET_API_KEYSecretAPI key from https://serpjet.io/signup (free tier: 1,000 searches/month)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npmserpjet-mcp0.1.1stdio

Tools

Saved tool list · updated 2w ago

Parameter	Type	Required	Description
q	string	Yes	Search query
gl	string	No	Country code for geo-targeted results, e.g. 'us', 'de', 'jp'
hl	string	No	Interface language, e.g. 'en', 'zh-cn'
num	integer	No	Number of results
page	integer	No	Result page (default: 1)
type	enum	No	Result type (default: search). Use 'shopping' for product prices.search \| images \| videos \| news \| shopping \| maps \| places \| scholar \| patents \| autocomplete

Details

From the project README

SERPJET MCP Server

Give your AI agent Google Search. 1,000 free searches/month — recurring, no credit card.

An MCP (Model Context Protocol) server for SERPJET — a Google SERP API that returns clean, structured JSON for 10 result types: web search, images, videos, news, shopping (with prices), maps, places, scholar, patents, and autocomplete.

Why SERPJET

1,000 searches/month free, forever — quota resets monthly (not a one-time trial credit)
No credit card required — sign up with just an email
10 result types in one tool, including Google Shopping with price fields
Country targeting via gl parameter (us, de, jp, ...)
Paid plans from $5, billed per successful request only

Quick start

Get a free API key at serpjet.io/signup
Add to your MCP client config:

Claude Desktop / Claude Code

{
  "mcpServers": {
    "serpjet": {
      "command": "npx",
      "args": ["-y", "serpjet-mcp"],
      "env": {
        "SERPJET_API_KEY": "sj_your_key_here"
      }
    }
  }
}

Cursor / Windsurf

Same config shape — add the serpjet entry to your MCP settings with SERPJET_API_KEY in env.

Tool

`google_search`

Parameter	Type	Description
`q`	string (required)	Search query
`type`	enum	`search` (default), `images`, `videos`, `news`, `shopping`, `maps`, `places`, `scholar`, `patents`, `autocomplete`
`gl`	string	Country code for geo-targeting, e.g. `us`, `de`, `jp`
`hl`	string	Language, e.g. `en`, `zh-cn`
`num`	number	Number of results (1–100)
`page`	number	Result page

Returns the raw SERPJET JSON response. Example — ask your agent:

"What does an Anker 20000mAh power bank cost right now in the US?"

The agent calls google_search with {"q": "anker 20000mah power bank", "type": "shopping", "gl": "us"} and gets back 40 offers with live prices and sellers.

Environment variables

Variable	Required	Description
`SERPJET_API_KEY`	yes	Your API key from serpjet.io
`SERPJET_API_BASE`	no	Override API base URL (default `https://api.serpjet.io`)

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.