SearXNG MCP Server
Enables web search through SearXNG instances, offering tools for general and category-specific queries, engine selection, time filtering, and engine discovery.
README
SearXNG MCP Server
A Model Context Protocol (MCP) server that provides web search capabilities through SearXNG instances.
Features
- 🔍 Web Search — Query any SearXNG instance for general web results
- 📁 Category-Specific Search — Search images, videos, news, music, science, etc.
- ⚙️ Engine Selection — Use specific search engines (Google, Bing, DuckDuckGo, etc.)
- 🕐 Time Filtering — Filter results by day, week, month, or year
- 📋 Engine Discovery — List all available SearXNG engines
Installation
From PyPI (when published)
pip install searxng-mcp-server
From Source
git clone https://github.com/<username>/searxng-mcp-server.git
cd searxng-mcp-server
pip install -e ".[dev]"
Configuration
Set the following environment variables:
| Variable | Description | Default |
|---|---|---|
SEARXNG_URL |
SearXNG instance URL | http://localhost:8888 (local Docker) |
SEARXNG_ENGINES |
Comma-separated engine list | (none — uses all) |
SEARXNG_LANG |
Search language code | en-US |
Example:
export SEARXNG_URL="http://localhost:8888"
export SEARXNG_ENGINES="google,bing,duckduckgo"
export SEARXNG_LANG="zh-TW"
Usage with Hermes Agent
Add to ~/.hermes/config.yaml:
mcp_servers:
searxng:
command: "uv"
args: ["run", "--directory", "/path/to/searxng-mcp-server", "searxng-mcp"]
env:
SEARXNG_URL: "https://search.sapti.me"
Usage with Claude Desktop / Cursor / VS Code
Add to your MCP configuration:
{
"mcpServers": {
"searxng": {
"command": "uv",
"args": ["run", "--directory", "/path/to/searxng-mcp-server", "searxng-mcp"],
"env": {
"SEARXNG_URL": "https://search.sapti.me"
}
}
}
}
Available Tools
search_web
Search the web using a SearXNG instance.
Parameters:
query(string, required): The search querymax_results(int, optional): Maximum results to return (default: 10)time_range(string, optional): Filter by time — 'day', 'week', 'month', 'year'
search_specific
Search using specific categories and/or engines.
Parameters:
query(string, required): The search querycategories(list of strings, optional): Categories to search (general, images, videos, news, music, files, it, science, social media)engines(list of strings, optional): Specific engines to usemax_results(int, optional): Maximum results (default: 10)time_range(string, optional): Time filter
search_by_category
Search a specific SearXNG category.
Parameters:
query(string, required): The search querycategory(string, optional): Category to search (default: 'general')max_results(int, optional): Maximum results (default: 10)
list_engines
List all available SearXNG search engines from searxng.org.
Parameters: None
Development
# Install dependencies
pip install -e ".[dev]"
# Run tests
pytest tests/
# Lint with ruff
ruff check src/ tests/
Public SearXNG Instances
You can use any public or self-hosted SearXNG instance. Some public instances:
https://search.sapti.mehttps://searx.behttps://search.ononoki.org
⚠️ Note: Public instances may have rate limits or be unreliable. For production use, consider self-hosting your own SearXNG instance.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。