SearXNG

An MCP server implementation that integrates with SearXNG, providing privacy-focused meta search capabilities.
  • javascript

27

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "kevinwatt-mcp-server-searxng": {
      "command": "npx",
      "args": [
        "-y",
        "@kevinwatt/mcp-server-searxng"
      ],
      "env": {
        "SEARXNG_INSTANCES": "http://localhost:8080",
        "SEARXNG_USER_AGENT": "MCP-SearXNG/1.0",
        "NODE_TLS_REJECT_UNAUTHORIZED": "0"
      }
    }
  }
}

You run a privacy-focused MCP server that integrates with SearXNG to perform meta searches across multiple engines without tracking users. This server exposes a simple MCP interface you can connect to from your MCP clients, enabling configurable search categories, languages, time ranges, and safe search levels while relying on a local or remote SearXNG instance.

How to use

Connect to the SearXNG MCP Server from your MCP client by referencing the available MCP endpoint configurations. You can run the server directly on your machine or start it via your MCP client’s runtime integration.

How to install

Prerequisites you need before installing this MCP server are Node.js and npm. Ensure Node.js is installed and accessible in your shell by running node -v and npm -v.

Option 1: Install using a package manager global install (manual installation):

npm install -g @kevinwatt/mcp-server-searxng

Option 2: Install via Smithery for automatic client integration (example shown for a Claude Desktop client):

npx -y @smithery/cli install @kevinwatt/mcp-server-searxng --client claude

Available tools

web_search

Execute meta searches across multiple engines with configurable language, categories, time range, and safesearch level

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational