Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิด┌─────────────────────────────────────────────────────────────┐
│ 🔍 Yandex Search MCP - Unofficial Community Project │
│ ⚡ Powered by Playwright + TypeScript + MCP Framework │
│ 🚀 Enhanced with Content Extraction & LLM Context │
└─────────────────────────────────────────────────────────────┘
⚠️ IMPORTANT DISCLAIMER
This is an unofficial community project and is not affiliated with, endorsed by, or connected to:
- Yandex LLC (the search engine provider)
- Anthropic (creators of Claude and MCP)
- Google (Playwright maintainers)
This tool uses browser automation to access Yandex search. Users are responsible for:
- Complying with Yandex's Terms of Service
- Respecting rate limits and bot policies
- Using their own authentication cookies
- Not using this tool for malicious purposes
# 1. Clone the repository
git clone https://github.com/bpawnzZ/yandex-search-mcp.git
cd yandex-search-mcp
# 2. Install dependencies
npm install
# 3. Build the project
npm run build
# 4. Configure cookies (see Cookie Setup section)
# 5. Add to MCP client configuration
# 6. Start searching! 🎉
git clone https://github.com/bpawnzZ/yandex-search-mcp.git
cd yandex-search-mcp
npm install
npm run build
npx yandex-search-mcp
Yandex implements CAPTCHA challenges for automated requests. Using authenticated cookies allows the tool to bypass these challenges and perform searches seamlessly.
Install Cookie-Editor Extension:
Log in to Yandex:
Export Cookies:
Save Cookies:
cookies/yandex-cookies.json[
{
"domain": ".yandex.com",
"expirationDate": 1800000000.000000,
"hostOnly": false,
"httpOnly": true,
"name": "Session_id",
"path": "/",
"sameSite": "no_restriction",
"secure": true,
"session": false,
"storeId": null,
"value": "YOUR_SESSION_ID_HERE"
}
]
Important: Keep your cookies secure and don't commit them to public repositories!
Add to your claude_desktop_config.json:
{
"mcpServers": {
"yandex-search": {
"command": "node",
"args": ["/path/to/yandex-search-mcp/dist/index.js"],
"env": {
"NODE_ENV": "production"
}
}
}
}
Add to ~/.kilocode/mcp.json:
{
"mcpServers": {
"yandex-search": {
"command": "node",
"args": ["/home/insomnia/git/yandex-search-mcp/dist/index.js"]
}
}
}
# Optional configuration
MAX_PAGES_PER_QUERY=5 # Default: 3
MAX_TOKENS_PER_PAGE=4000 # Default: 3000
CACHE_TTL_HOURS=24 # Default: 24
// Simple search - returns titles, URLs, snippets
{
"tool": "yandex_search",
"params": {
"query": "artificial intelligence",
"numResults": 10,
"region": "com",
"language": "en"
}
}
// Enhanced search - fetches and analyzes page content
{
"tool": "yandex_search_enhanced",
"params": {
"query": "artificial intelligence benefits",
"numResults": 5,
"region": "com",
"fetch_content": true,
"max_pages": 3,
"max_tokens_per_page": 3000,
"analysis_level": "detailed",
"context_format": "synthesized"
}
}
The enhanced tool supports multiple output formats:
{
"summary": "Based on 3 sources (12,456 words analyzed), here is what we found about \"artificial intelligence benefits\":",
"key_findings": [
{
"source": "example.com",
"finding": "AI increases productivity by 40% in manufacturing",
"confidence": "high"
}
],
"synthesized_knowledge": "Synthesis of findings...",
"source_references": [
{
"url": "https://example.com/ai-benefits",
"title": "AI Benefits in 2026",
"key_points": ["Increased productivity", "Cost reduction"],
"relevance_note": "Relevance score: 85.3/100"
}
],
"metadata": {
"query": "artificial intelligence benefits",
"total_results": 500,
"pages_fetched": 3,
"successful_extractions": 3,
"total_time_ms": 28500
}
}
Simple search tool returning titles, URLs, and snippets.
Parameters:
query (string, required): Search querynumResults (number, optional): Number of results (default: 10, max: 50)region (string, optional): Region code (default: "com")language (string, optional): Language code (default: "en")safeSearch (boolean, optional): Enable safe search (default: true)Full-featured search with content extraction and analysis.
Parameters:
fetch_content (boolean, optional): Fetch page content (default: true)max_pages (number, optional): Max pages to fetch (default: 3, max: 10)max_tokens_per_page (number, optional): Token limit per page (default: 3000)analysis_level (enum, optional): "basic" | "detailed" | "comprehensive"context_format (enum, optional): "raw" | "summarized" | "synthesized" | "qa_ready"┌──────────────────────────────────────────────────────────────┐
│ Yandex Search MCP │
├──────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────┐ ┌──────────────────────────────────┐ │
│ │ Basic Search │ │ Enhanced Pipeline │ │
│ │ │ │ │ │
│ │ • Search │ │ ┌─────────────┐ ┌──────────┐ │ │
│ │ • Snippets │ │ │ Browser │→ │ Search │ │ │
│ │ • URLs │ │ │ Manager │ │ │ │ │
│ └──────────────┘ │ └─────────────┘ └────┬─────┘ │ │
│ │ │ │ │
│ │ ┌─────────────┐ ┌────▼─────┐ │ │
│ │ │ Content │ │ Extract │ │ │
│ │ │ Extractor │←─┤ Content │ │ │
│ │ └─────────────┘ └────┬─────┘ │ │
│ │ │ │ │
│ │ ┌─────────────┐ ┌────▼─────┐ │ │
│ │ │ Relevance │ │ Cache │ │ │
│ │ │ Scorer │←─┤ (LRU) │ │ │
│ │ └─────────────┘ └──────────┘ │ │
│ │ │ │ │
│ │ ┌──────────────────┐ │ │ │
│ │ │ LLM Context │←─┘ │ │
│ │ │ Formatter │ │ │
│ │ └──────────────────┘ │ │
│ │ │ │ │
│ │ ┌──────────────────┐ │ │ │
│ │ │ Structured │←─┘ │ │
│ │ │ JSON Output │ │ │
│ │ └──────────────────┘ │ │
│ └──────────────────────────────────┘ │
│ │
└──────────────────────────────────────────────────────────────┘
Symptom: Results contain error: 'CAPTCHA detected'
Solutions (in order of effectiveness):
Use Yandex Search API (Recommended - 100% reliable):
export YANDEX_SEARCH_API_KEY="your_api_key"
export YANDEX_SEARCH_USER_ID="your_user_id"
See Yandex Search API Setup below.
Update Cookies: Re-export fresh cookies from your browser
Use Residential Proxy: Datacenter IPs are often flagged
Enable FlareSolverr: Add FLARESOLVERR_URL environment variable
The most reliable way to avoid CAPTCHA is using the official Yandex Search API:
Get API Credentials:
yandex.search-api.execute scopeConfigure MCP:
{
"mcpServers": {
"yandex-search": {
"command": "node",
"args": ["/path/to/yandex-search-mcp/dist/index.js"],
"env": {
"YANDEX_SEARCH_API_KEY": "your_api_key_here",
"YANDEX_SEARCH_USER_ID": "your_user_id_here"
}
}
}
}
Benefits:
Symptom: sameSite: expected one of (Strict|Lax|None)
Solution: This is automatically handled by the cookie normalization in BrowserManager.
Symptom: Empty or minimal content from pages
Possible Causes:
Solution:
max_pages parametermax_tokens_per_pageContributions are welcome! Please:
git checkout -b feature/amazing-feature)git commit -m 'Add amazing feature')git push origin feature/amazing-feature)This project is licensed under the MIT License - see the LICENSE file for details.
Made with ⚡ by the community, for the community.
This is an unofficial tool. Please use responsibly and respect Yandex's Terms of Service.
UNOFFICIAL - A Model Context Protocol (MCP) server that enables AI assistants to perform web searches using Yandex. Built with Playwright for reliable browser automation and stealth capabilities.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Yandex Search ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 UNOFFICIAL - A Model Context Protocol (MCP) server that enables AI assistants to perform web searches using Yandex. Built with Playwright for reliable browser automation and stealth capabilities.