Provides access to Google Search results via SERPJET API, supporting web search, images, videos, news, shopping, maps, places, scholar, patents, and autocomplete.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SERPJET MCP Server What is the current price of an Anker 20000mAh power bank in the US?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
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
Related MCP server: You.com MCP Server
Get a free API key at serpjet.io/signup
Add to your MCP client config:
{
"mcpServers": {
"serpjet": {
"command": "npx",
"args": ["-y", "serpjet-mcp"],
"env": {
"SERPJET_API_KEY": "sj_your_key_here"
}
}
}
}Same config shape — add the serpjet entry to your MCP settings with SERPJET_API_KEY in env.
google_searchParameter | Type | Description |
| string (required) | Search query |
| enum |
|
| string | Country code for geo-targeting, e.g. |
| string | Language, e.g. |
| number | Number of results (1–100) |
| 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 |
| yes | Your API key from serpjet.io |
| no | Override API base URL (default |
MIT
Search Google and get structured JSON results via SERPJET (serpjet.io). Supports 10 result types: web search, images, videos, news, shopping (with prices), maps, places, scholar, patents, and autocomplete. Free tier: 1,000 searches/month, recurring. Each successful call uses 1 credit.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query | |
| gl | No | Country code for geo-targeted results, e.g. 'us', 'de', 'jp' | |
| hl | No | Interface language, e.g. 'en', 'zh-cn' | |
| num | No | Number of results | |
| page | No | Result page (default: 1) | |
| type | No | Result type (default: search). Use 'shopping' for product prices. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description bears full burden. It discloses credit consumption (1 per successful call) and the free tier limit (1,000 searches/month), which are behavioral traits. However, it omits rate limits, error handling, or any destructive behavior potential. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long, front-loaded with the core purpose, followed by a list of result types and cost details. Every sentence provides essential information without redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should compensate by explaining the return format, but it only says 'structured JSON results' without details (e.g., pagination, fields). It does provide free tier and credit context, which is helpful. Overall adequate for a simple search tool but missing return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds a minor extra note for the 'type' parameter ('Use 'shopping' for product prices') which slightly enhances understanding beyond the enum. No other parameter details are added beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Google and returns structured JSON via SERPJET, listing 10 supported result types. This provides a specific verb (search) and resource (Google) with scope (10 types), leaving no ambiguity about its function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No sibling tools are provided, so explicit alternatives are absent. The description does not specify when to use or not use this tool, but it does mention the free tier and credit usage, which indirectly informs usage decisions. Lacks explicit guidance on prerequisites or exclusion cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0google_searchScored across 1 tool
With only a single tool, there is no risk of confusing different tools. The tool's purpose is clearly defined.
There is only one tool, so naming consistency is moot. The name 'google_search' is clear and follows a common verb_noun pattern.
The server has a single tool, which is slightly thin for a search service that supports multiple result types. However, the tool is comprehensive enough to cover many use cases, making it reasonable.
The tool covers 10 different search result types (web, images, videos, news, shopping, maps, places, scholar, patents, autocomplete), leaving no obvious gaps for a search tool.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
Live web search for AI agents. $0.001/call, x402 on Base, no API key.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
