What are the prerequisites for running the server?
Python 3.9+ and access to a running SearXNG instance (local or remote) are required. Docker and uv are optional for containerized or faster setup.
@The-AI-Workshops
基本信息
An MCP sse implementation of the Model Context Protocol (MCP) server integrated with SearXNG for providing AI agents with powerful, privacy-respecting search capabilities.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"searxng-mcp-server": {
"command": "docker",
"args": [
"run",
"-d",
"--name=searxng",
"-p",
"32768:8080",
"-v",
"/root/searxng:/etc/searxng",
"\\"
]
}
}
}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。
The SearXNG MCP Server is an MCP SSE implementation that integrates the SearXNG metasearch engine with the Model Context Protocol. It enables AI agents to perform privacy-respecting web searches through a SearXNG instance. The server serves both as a ready-to-use tool and as a template for building custom MCP servers.
Install the server using uv, Docker, or Smithery. Ensure Python 3.9+ and a running SearXNG instance are available. Configure a .env file with SEARXNG_BASE_URL, HOST, PORT, and TRANSPORT (sse or stdio). Run server.py directly, via Docker, or through Smithery depending on your chosen transport. Connect your MCP client (e.g., Claude Desktop, Windsurf) using the appropriate SSE URL or stdio configuration.
Python 3.9+ and access to a running SearXNG instance (local or remote) are required. Docker and uv are optional for containerized or faster setup.
The server supports both SSE (Server-Sent Events) and stdio transports. Set the `TRANSPORT` environment variable to `sse` or `stdio` in your `.env` file.
Set the `SEARXNG_BASE_URL` environment variable in your `.env` file, for example `http://172.17.0.1:32768` (default Docker bridge address).
Yes, n8n users should use `host.docker.internal` instead of `localhost` in the SSE URL because n8n runs inside a separate container.
Yes, the repository is designed as a template. Add custom tools by decorating methods with `@mcp.tool()`, and add resources or prompts with `@mcp.resource()` and `@mcp.prompt()`.
不止于 CSS

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论