What is the difference between this server and using SearXNG directly?
This server wraps SearXNG’s JSON API into an MCP tool (`web_search`), making it easy to integrate into MCP‑compatible apps without manual API calls.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"kevinwatt_mcp-server-searxng": {
"command": "docker",
"args": [
"run",
"-d",
"\\"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
SearXNG MCP Server integrates SearXNG's privacy-focused meta search capabilities with the Model Context Protocol, enabling privacy-preserving web searches across multiple engines. It is intended for developers and AI agents that need tracking-free, configurable search results.
Install globally via npm (npm install -g @kevinwatt/mcp-server-searxng) and run directly with mcp-server-searxng. Alternatively, configure it as an MCP server in Dive Desktop by providing the JSON configuration shown in the README. A local SearXNG instance (e.g., Docker) is required; environment variable SEARXNG_INSTANCES can specify custom URLs.
This server wraps SearXNG’s JSON API into an MCP tool (`web_search`), making it easy to integrate into MCP‑compatible apps without manual API calls.
A running SearXNG instance reachable via HTTP (default `http://localhost:8080`). Node.js and npm are needed to install the server package.
Set the `SEARXNG_INSTANCES` environment variable as a comma‑separated list of URLs. The default is `http://localhost:8080`.
Yes. The `web_search` tool accepts optional parameters `categories`, `time_range`, `language`, `safesearch`, and `page`.
The server itself does not track or profile users; it delegates to SearXNG, which also does not track users across searches. No user data is stored by the server.

Model Context Protocol Servers
MCP Toolbox for Databases is an open source MCP server for databases.
Painless E2E Automation for Mobile and Web
Hindsight: Agent Memory That Learns

Model Context Protocol Servers
评论