MCP.so
Sign In

mcp-searxng-public

@pwilkin

Repository

About mcp-searxng-public

An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result

#mcp-searxng#mcp-server#search-engine

Basic information

Category

Other

License

MIT

Runtime

node

Transports

stdio

Publisher

pwilkin

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "SearXNGScraper": {
      "command": "npx",
      "args": [
        "mcp-searxng-public"
      ],
      "capabilities": {
        "tool-calls": true
      },
      "env": {
        "SEARXNG_BASE_URL": "https://metacat.online;https://nyc1.sx.ggtyler.dev;https://ooglester.com;https://search.080609.xyz;https://search.canine.tools;https://search.catboy.house;https://search.citw.lgbt;https://search.einfachzocken.eu;https://search.federicociro.com;https://search.hbubli.cc;https://search.im-in.space;https://search.indst.eu",
        "DEFAULT_LANGUAGE": "en"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-searxng-public?

mcp-searxng-public is an MCP server that queries up to three public SearXNG instances, parsing HTML search results into a JSON format. It is designed for users who need a reliable search tool that works with public SearXNG servers that typically do not expose JSON APIs.

How to use mcp-searxng-public?

Install via npm install mcp-searxng-public. Configure with SEARXNG_BASE_URL (semicolon-separated list of URLs) and DEFAULT_LANGUAGE. Invoke the search tool with required query and optional time_range, language, and detailed arguments. Run the report task to get a list of accessible servers.

Key features of mcp-searxng-public

  • Queries multiple public SearXNG instances with failover.
  • Parses HTML results into structured JSON with URL and summary.
  • Supports optional time range (day, month, year).
  • Supports optional language parameter with configurable default.
  • Detailed mode queries up to 3 servers and multiple pages.
  • Returns deduplicated results from fallback servers.

Use cases of mcp-searxng-public

  • Privacy-focused web searches using public SearXNG instances.
  • Automated search queries in AI agents or workflows.
  • Getting search results without needing a private SearXNG instance.
  • Fallback search capability for high availability.

FAQ from mcp-searxng-public

How does mcp-searxng-public differ from other SearXNG MCP servers?

Most SearXNG MCP servers use the JSON output format, which fails on public servers. This server parses HTML from public instances and includes fallback servers for reliability.

What environment variables are required?

SEARXNG_BASE_URL: a semicolon-separated list of SearXNG URLs (default list provided). DEFAULT_LANGUAGE: language code (e.g., en). Optional, falls back to no language if unset.

Where does the search data come from?

Data comes from public SearXNG instances specified in the SEARXNG_BASE_URL environment variable. The server reads up to three of these, using the first as primary and others as fallback.

What transport or authentication does the server use?

The server communicates via the Standard Input/Output (stdio) transport. No authentication is configured; it relies on public SearXNG instances.

Are there any known limitations?

The server relies on publicly accessible SearXNG instances, which may have rate limits or become unavailable. It parses HTML, so result structure may change if instance UI updates.

Comments

More Other MCP servers

Nginx UI

0xJacky

Yet another WebUI for Nginx

11.3K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K

Mobile Mcp

mobile-next

Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

5.4K