The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Serpjet MCP listing page.
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.
gl parameter (us, de, jp, ...)Same config shape — add the serpjet entry to your MCP settings with SERPJET_API_KEY in env.
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.
| 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) |
MIT