mcp-searxng
Integrates SearXNG API to give AI assistants web search and URL reading capabilities.
README
SearXNG MCP Server
An MCP server that integrates the SearXNG API, giving AI assistants web search and URL reading capabilities.
Quick Start
Requires Bun.
Add the server to your MCP client configuration:
{
"mcpServers": {
"searxng": {
"command": "bunx",
"args": ["@tterrasson/mcp-searxng"],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Replace YOUR_SEARXNG_INSTANCE_URL with the URL of your SearXNG instance, for example https://search.example.com.
Features
- Web Search: General queries, news, articles, with pagination.
- URL Content Reading: Content extraction powered by Readability (Firefox Reader Mode). Strips navigation, ads, and boilerplate before converting to Markdown, with pagination, section filtering, and heading extraction.
- Pagination: Control which page of results to retrieve.
- Time Filtering: Filter results by time range: day, month, or year.
- Language Selection: Filter results by preferred language.
- Safe Search: Control the search result filtering level.
- Category Filtering: Restrict results to specific engine types (news, images, science, etc.).
How It Works
mcp-searxng is a standalone MCP server that runs with Bun. Your AI assistant connects to it through the MCP protocol, and the server queries any SearXNG instance through its HTTP JSON API.
Not a SearXNG plugin: This project cannot be installed as a native SearXNG plugin. Point it at an existing SearXNG instance by setting
SEARXNG_URL.
AI Assistant
| MCP protocol
v
mcp-searxng (this project, Bun process)
| HTTP JSON API (SEARXNG_URL)
v
SearXNG instance
Tools
web_search
Execute web searches with pagination.
Inputs:
query(string): The search query. This string is passed to external search services.pageno(number, optional): Search page number, starts at 1. Default:1.time_range(string, optional): Filter results by time range. One ofday,month,year.language(string, optional): Language code for results, for exampleen,fr,de, orall. Default:all.safesearch(number, optional): Safe search filter level, where0is none,1is moderate, and2is strict. Defaults to the SearXNG instance setting.categories(string, optional): Comma-separated list of search categories to filter results by engine type. Available values:general,images,videos,news,map,music,it,science,files,social media. Defaults to the SearXNG instance setting.
web_url_read
Read and convert the content from a URL to Markdown.
Inputs:
url(string): The URL to fetch and process.startChar(number, optional): Starting character position for content extraction. Default:0.maxLength(number, optional): Maximum number of characters to return.section(string, optional): Extract content under a specific heading.readHeadings(boolean, optional): Return only a list of headings instead of full content.
Installation
This fork is intended to run with Bun.
git clone https://github.com/tterrasson/mcp-searxng.git
cd mcp-searxng
bun install
bun run build
Use bun dist/index.js in MCP clients after building.
For local development, you can run the TypeScript entrypoint directly:
SEARXNG_URL=http://localhost:8080 bun src/index.ts
HTTP Transport
By default the server uses STDIO. Set MCP_HTTP_PORT to enable HTTP mode:
{
"mcpServers": {
"searxng-http": {
"command": "bun",
"args": ["/absolute/path/to/mcp-searxng/dist/index.js"],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
"MCP_HTTP_PORT": "3000"
}
}
}
}
Endpoints:
POST/GET/DELETE /mcp: MCP protocolGET /health: health check
Run it locally:
MCP_HTTP_PORT=3000 SEARXNG_URL=http://localhost:8080 bun dist/index.js
curl http://localhost:3000/health
Configuration
Set SEARXNG_URL to your SearXNG instance URL. All other variables are optional.
Client compatibility (PLAIN_TEXT_CONTENT)
By default, web_search returns results only via structuredContent (the MCP structured data field). Clients that do not support structuredContent — such as LM Studio — will see an empty response.
Set PLAIN_TEXT_CONTENT to any non-empty value to also include results as plain text in the standard content field:
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
"PLAIN_TEXT_CONTENT": "true"
}
Full environment variable reference: CONFIGURATION.md
Troubleshooting
403 Forbidden from SearXNG
Your SearXNG instance likely has JSON format disabled. Edit settings.yml, usually /etc/searxng/settings.yml:
search:
formats:
- html
- json
Restart your SearXNG service, then verify:
curl 'http://localhost:8080/search?q=test&format=json'
You should receive a JSON response. If not, confirm the file is correctly loaded and YAML indentation is valid.
See also: SearXNG settings docs and SearXNG discussion #1789.
Development
bun install
bun run build
bun run lint
bun test tests
Use the MCP inspector:
bun run inspector
Contributing
See CONTRIBUTING.md.
License
MIT. See LICENSE for details.
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。