Advertise
MCP.so
Sign In

SearXNG MCP Server

@MCP-Mirror

Repository

Basic information

Category

Other

Transports

stdio

Author

MCP-Mirror

About SearXNG MCP Server

Mirror of

#mcp-server#searxng#meta-search

SearXNG MCP Server config

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

{
  "mcpServers": {
    "kevinwatt_mcp-server-searxng": {
      "command": "docker",
      "args": [
        "run",
        "-d",
        "\\"
      ]
    }
  }
}

SearXNG MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is SearXNG MCP Server?

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.

How to use SearXNG MCP Server?

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.

Key features of SearXNG MCP Server

  • Meta search combining results from multiple engines
  • Privacy-first design with no tracking or profiling
  • Multi‑category support: general, news, science, files, images, videos, and more
  • Language‑specific search and time‑range filters (day, week, month, year)
  • Three‑level safe search filtering and fallback to multiple SearXNG instances

Use cases of SearXNG MCP Server

  • Privacy-conscious web searches from AI assistants
  • Aggregated search across categories (news, images, videos) in a single call
  • Fallback‑resilient search setups with multiple SearXNG instances

Frequently asked questions

1

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.

2

What are the runtime requirements?

A running SearXNG instance reachable via HTTP (default `http://localhost:8080`). Node.js and npm are needed to install the server package.

3

How can I provide custom SearXNG instances?

Set the `SEARXNG_INSTANCES` environment variable as a comma‑separated list of URLs. The default is `http://localhost:8080`.

4

Can I filter search results by time or category?

Yes. The `web_search` tool accepts optional parameters `categories`, `time_range`, `language`, `safesearch`, and `page`.

5

How does the server handle privacy?

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.

Comments

More Other MCP servers

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K
N

Next Generation Movers: free moving quotes (remote MCP)

Next Generation Movers

Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Advertise