跳到正文 SearXNG MCP Server
A powerful Model Context Protocol (MCP) server providing comprehensive search capabilities that rival , , and other commercial search services. Powered by , aggregating results from including Google, Bing, DuckDuckGo, Brave, and more.
MCP server for SearXNG web search - free, private, multi-engine search for AI agents
把任意工具接入任意智能体。面向非开发者的 MCP 服务器目录;网关承载流量,n8n 承载应用。
产品
目录
开发者
公司
Brave Search API
Perplexity
89+ search engines
🌟 Features
Search Tools (7 Total)
Key Capabilities
🔒 Privacy-First : Self-hosted, no data leaves your machine
💰 Free Forever : No API keys, no usage limits, no credit cards
🌐 89+ Search Engines : Aggregates Google, Bing, DDG, Brave, Qwant, Startpage, Mojeek, and more
⚡ Fast : Local caching, concurrent requests
🎯 Accurate : Multiple engine verification, relevance scoring
🌍 Multi-Language : Support for 20+ languages
🔍 Advanced Filters : Time ranges, safe search, specific engines
📊 Rich Results : Images, videos, news, code, and web content
📋 Table of Contents
🚀 Installation
Prerequisites
Rust 1.75+ (for building from source)
Docker (for running SearXNG)
Git
Option 1: Build from Source # Clone the repository
git clone https://github.com/yourusername/searxng-mcp.git
cd searxng-mcp
# Build release binary
cargo build --release
# The binary will be at target/release/searxng-mcp
Option 2: Install via Cargo
Option 3: Using Install Script curl -fsSL https://raw.githubusercontent.com/yourusername/searxng-mcp/main/install.sh | bash
⚡ Quick Start
1. Start SearXNG (Docker) # Create config directory
mkdir -p ~/.config/searxng
# Run SearXNG container
docker run -d \
--name searxng \
-p 8888:8080 \
-v "$HOME/.config/searxng:/etc/searxng" \
--restart unless-stopped \
searxng/searxng:latest
# Verify it's working
curl http://localhost:8888/healthz
2. Configure Your MCP Client Add to your MCP client configuration:
{
"mcpServers": {
"searxng": {
"command": "/path/to/searxng-mcp",
"env": {
"SEARXNG_URL": "http://localhost:8888",
"RUST_LOG": "info"
}
}
}
}
3. Start Searching! Your AI assistant can now use these tools:
web_search - Search the web
image_search - Find images
news_search - Get news articles
video_search - Search videos
technical_search - Find code and docs
fetch_url - Extract content from URLs
🔧 Configuration
Environment Variables
SearXNG Settings Create ~/.config/searxng/settings.yml:
use_default_settings: true
general:
instance_name: "SearXNG MCP"
server:
port: 8080
bind_address: "0.0.0.0"
search:
safe_search: 0
autocomplete: "duckduckgo"
formats:
- html
- json
engines:
- name: google
engine: google
disabled: false
- name: bing
engine: bing
disabled: false
- name: duckduckgo
engine: duckduckgo
disabled: false
- name: brave
engine: brave
disabled: false
- name: github
engine: github
disabled: false
- name: stackoverflow
engine: stackoverflow
disabled: false
- name: wikipedia
engine: wikipedia
disabled: false
💡 Usage Examples
Web Search {
"name": "web_search",
"arguments": {
"query": "machine learning frameworks",
"max_results": 10,
"time_range": "month",
"language": "en"
}
}
News Search {
"name": "news_search",
"arguments": {
"query": "AI regulation",
"time_range": "week",
"max_results": 10
}
}
Image Search {
"name": "image_search",
"arguments": {
"query": "rust programming logo transparent",
"max_results": 5
}
}
Fetch URL Content {
"name": "fetch_url",
"arguments": {
"url": "https://www.rust-lang.org/",
"max_length": 5000
}
}
🔌 Integrations
Claude Desktop macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"searxng": {
"command": "/path/to/searxng-mcp",
"env": {
"SEARXNG_URL": "http://localhost:8888"
}
}
}
}
Kimi Code CLI Add to Kimi Code CLI MCP settings:
{
"mcpServers": {
"searxng": {
"command": "/path/to/searxng-mcp",
"env": {
"SEARXNG_URL": "http://localhost:8888"
}
}
}
}
Clawdbot / Moltbot # Install wrapper tools
cp scripts/moltbot-web-tool ~/.local/bin/
chmod +x ~/.local/bin/moltbot-web-tool
# Configure clawdbot to use SearXNG
echo 'export SEARXNG_URL=http://localhost:8888' >> ~/.clawdbot/.env
Other MCP Clients Any MCP-compatible client can use this server:
Configure the client with the server path
Set SEARXNG_URL environment variable
The client will auto-discover available tools
📚 API Reference
Tool Schemas
web_search
news_search
fetch_url
Response Format All tools return markdown-formatted text:
## Search Results for: "query"
Estimated total results: 150
Showing 10 results:
### 1. Result Title
**URL:** https://example.com
Result snippet text...
*📅 2024-01-15 | 🔍 Found by: google, bing | ⭐ Score: 8.5 | 📂 Category: general*
---
🐳 Docker Setup
Docker Compose version: '3.8'
services:
searxng:
image: searxng/searxng:latest
container_name: searxng
ports:
- "8888:8080"
volumes:
- ./config:/etc/searxng
environment:
- BASE_URL=http://localhost:8888/
restart: unless-stopped
Run with: docker-compose up -d
Advanced Docker Configuration # With custom settings
docker run -d \
--name searxng \
-p 8888:8080 \
-v "$HOME/.config/searxng/settings.yml:/etc/searxng/settings.yml:ro" \
-e "BASE_URL=http://localhost:8888/" \
-e "INSTANCE_NAME=SearXNG MCP" \
--restart unless-stopped \
searxng/searxng:latest
🔍 Comparison with Commercial APIs
🐛 Troubleshooting
Server won't start # Check SearXNG is running
curl http://localhost:8888/healthz
# Check SearXNG logs
docker logs searxng
# Verify binary
cargo build --release
./target/release/searxng-mcp --version
No search results # Verify engines are enabled
curl http://localhost:8888/config | jq '.engines[] | select(.enabled) | .name'
# Test direct search
curl "http://localhost:8888/search?q=test&format=json" | jq '.results | length'
Connection refused # Ensure SEARXNG_URL has protocol
export SEARXNG_URL=http://localhost:8888 # ✅
export SEARXNG_URL=localhost:8888 # ❌
MCP Client not finding tools # Check server responds to initialization
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | ./target/release/searxng-mcp
🤝 Contributing Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request
📄 License This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
📞 Support
Brave Search Search the web with Brave's independent index — web, news, images, and videos. Bring your own subscription token from the [Brave Search API dashboard](https://api-dashboard.search.brave.com). Paper Search Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, and IACR. Fetch PDFs and extract full text to accelerate literature reviews. Get consistent Agent News The intelligence layer agents use before they act, sourced answers on the agent economy.
Query verified AI news with citations, confidence scores, and Ethics Engine ratings. Use instead of generic we PubMed Search biomedical literature across 36 million citations. Find papers, abstracts, and related articles from MEDLINE and life science journals. Gpt Researcher An autonomous agent that conducts deep research on any data using any LLM providers Emblem # EmblemAI MCP
EmblemAI is a hosted Model Context Protocol server that gives AI agents a full-featured crypto wallet plus **200+ tools** for trading, DeFi, NFTs, and on-chain analytics across **7 blo Web Scout Search the web and extract clean, readable text from webpages. Process multiple URLs at once to speed up research with reliable throttling and error handling. Quickly compile sources and summaries for Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a XERJ The search engine for AI agents: cited answers from your local code, docs, specs and logs. MCP Toolbox MCP Toolbox for Databases is an open source MCP server for databases. Pubmed Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms. Naver Search Search Naver across news, blogs, books, encyclopedia, cafe posts, Knowledge iN, local places, images, shopping, and professional documents. Returns Korean-language results and Korea-local content that Search MCP 服务器 最佳 Search MCP 服务器 ai-seo When the user wants to get cited and recommended in AI answers (ChatGPT, Perplexity, AI Overviews), or asks why AI cites a competitor, which content gets cited, or whether llms.txt or a page format is career-ops Open-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications. Use when the user pastes a job URL or JD, asks to scan portals, generate a CV/PDF, track application
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
如何安装 Searxng? 在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
Searxng 需要 API 密钥吗? 此记录未列出必需的环境变量。
Searxng 使用哪种传输方式? Searxng 通过 stdio 在本地运行。
Searxng 上次检查是什么时候? 上次检查时间:2026-10-28。 MCP server for SearXNG web search - free, private, multi-engine search for AI agents
工具
0 / 10