Serpex MCP
Serpex MCP
Model Context Protocol(MCP)サーバーで、Serpex API を通じてマルチエンジンのウェブ検索機能を提供します。Google、Bing、DuckDuckGo、Brave、Yahoo、Yandex を、自動エンジンルーティングと構造化された JSON 結果で検索できます。
機能
✅ マルチエンジン対応: 6つの検索エンジン(Google、Bing、DuckDuckGo、Brave、Yahoo、Yandex)にアクセス
✅ 自動ルーティング: 利用可能な最適な検索エンジンを自動選択
✅ 期間フィルタリング: 日、週、月、年の単位で結果をフィルタリング
✅ 構造化結果: クリーンで一貫性のあるJSONレスポンス
✅ 高速&信頼性: 組み込みのCAPTCHA処理とプロキシローテーション
✅ 簡単な統合: Claude Desktop、Jan AI、およびMCP互換のクライアントで動作
Related MCP server: Serper Search and Scrape MCP Server
インストール
クイックスタート(npx - 推奨)
インストールは不要です!npx で直接実行できます:
npx serpex-mcpグローバルインストール
npm install -g serpex-mcpローカルインストール
npm install serpex-mcp使用方法
Claude Desktopを使用する
Claude Desktopの設定(macOSでは ~/Library/Application Support/Claude/claude_desktop_config.json)に追加します:
{
"mcpServers": {
"serpex": {
"command": "npx",
"args": ["-y", "serpex-mcp"],
"env": {
"SERPEX_API_KEY": "your-api-key-here"
}
}
}
}他のMCPクライアントの場合
MCP互換のクライアントであれば、このサーバーを使用できます。次のように設定します:
コマンド:
npx引数:
-y serpex-mcp環境変数:
SERPEX_API_KEY=your-key
スタンドアロン
export SERPEX_API_KEY="your-api-key-here"
serpex-mcp利用可能なツール
serpex_search
Serpex マルチエンジン API を使用してウェブを検索します。オプションで、検索とインラインで上位結果のページ全体のコンテンツ(Markdown)を取得します。ベストエフォートのため、各結果の content と content_error を確認してください。
パラメータ:
q(必須): 検索クエリ文字列(最大500文字)include_content(オプション、boolean): 上位結果のページ全体のコンテンツ(Markdown)も取得します。ベストエフォートです。約79%の結果URLでコンテンツが返されますが、ブロックされたページやrobots.txtで許可されていないページでは代わりにcontent_errorが返されます。デフォルト:false。content_results(オプション、5 | 10):include_contentがtrueの場合にコンテンツを取得する上位結果の数。5または10のいずれかでなければなりません。デフォルトは5です。
例:
{
"q": "artificial intelligence trends 2025",
"include_content": true,
"content_results": 5
}レスポンス(JSON、ツール出力テキストとして)には、content_requested / content_delivered のカウントと、各結果ごとに成功時は content、失敗時は content_error が含まれます。コンテンツが要求されなかった場合は、両方のキーが省略されます。
APIキーの取得
serpex.dev にアクセスします
無料アカウントに登録します
ダッシュボードからAPIキーを取得します
それを
SERPEX_API_KEY環境変数で使用します
API情報
ベースURL:
https://api.serpex.devドキュメント: https://serpex.dev/docs
料金: 無料枠あり、手頃な価格の有料プラン
開発
ソースからビルド
git clone https://github.com/divyeshradadiya/serpex-mcp.git
cd serpex-mcp
pnpm install
pnpm buildテストを実行
export SERPEX_API_KEY="your-key-here"
pnpm testライセンス
MIT
リンク
Available Tools
1 toolserpex_searchB
Search the web using Serpex API. Returns structured search results from multiple engines (Google, Bing, DuckDuckGo, Brave, Yahoo, Yandex).
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query (max 500 characters) | |
| engine | No | Search engine (default: auto) | |
| time_range | No | Filter by time range |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the API and return type (structured results from multiple engines), but fails to disclose critical traits such as rate limits, authentication needs, error handling, or pagination. For a search tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
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 a single, efficient sentence that front-loads the core purpose ('Search the web using Serpex API') and adds necessary detail ('Returns structured search results from multiple engines'). Every word earns its place with no redundancy or waste.
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?
Given the complexity of a search API tool with no annotations and no output schema, the description is incomplete. It lacks information on response format, error cases, rate limits, and authentication requirements. While the input schema is well-covered, the overall context for effective tool use is insufficient.
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?
The schema description coverage is 100%, with all parameters well-documented in the input schema (e.g., query max length, engine options, time range enums). The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without compensating value.
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 action ('Search the web') and resource ('using Serpex API'), specifying it returns structured results from multiple engines. It's specific about the verb and resource, but since there are no sibling tools, it doesn't need to distinguish from alternatives, making it clear but not requiring sibling differentiation.
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?
The description implies usage for web searching with structured results from multiple engines, but provides no explicit guidance on when to use this tool versus alternatives (e.g., other search methods or APIs). Since there are no sibling tools, it doesn't need to differentiate, but it lacks context on optimal use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
serpex_search
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose: searching the web using the Serpex API.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'serpex_search' follows a clear and logical pattern, combining the server name with the action.
A single tool is too few for a web search server, as it lacks essential operations like filtering results, handling pagination, or accessing specific search engines individually. This minimal set limits functionality and may cause agent failures in complex tasks.
The tool surface is severely incomplete for a web search domain. While the search tool exists, there are significant gaps such as no ability to refine searches, manage result formats, or perform advanced queries, which are common in search APIs.
Maintenance
Related MCP Connectors
Web search, agentic search, news, page retrieval, sitemaps, and trending topics through Search1API.
Google, Bing, DuckDuckGo and Google Maps search results, free without an API key.
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables web search across multiple search engines (DuckDuckGo, Bing, Startpage) with parallel execution and result deduplication. Also provides web page content extraction capabilities.2-
- AlicenseBqualityDmaintenanceEnables web search via Serper API with advanced search operators and webpage scraping capabilities to extract content in plain text or markdown format.21,865 npmMIT
- AlicenseAqualityDmaintenanceEnables advanced web search across multiple search engines (Brave, DuckDuckGo, Google, Bing, Yandex) with intelligent backend selection, full content extraction, and advanced filtering by time, language, geography, and content type.3MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables searching across multiple search engines (Google, Bing, YouTube, DuckDuckGo, etc.) and retrieving parsed search results via SerpApi integration.-