0
0
Source

Search the web using a self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from multiple engines.

Install

mkdir -p .claude/skills/searxng && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8600" && unzip -o skill.zip -d .claude/skills/searxng && rm skill.zip

Installs to .claude/skills/searxng

About this skill

SearXNG Search Skill

Search the web using your self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from Google, DuckDuckGo, Brave, Startpage, and 70+ other engines.

Prerequisites

SearXNG running locally or on a server. Quick Docker setup:

mkdir -p ~/Projects/searxng/searxng
cd ~/Projects/searxng

# Create docker-compose.yml
cat > docker-compose.yml << 'EOF'
services:
  searxng:
    image: searxng/searxng:latest
    container_name: searxng
    ports:
      - "8080:8080"
    volumes:
      - ./searxng:/etc/searxng:rw
    environment:
      - SEARXNG_BASE_URL=http://localhost:8080/
    restart: unless-stopped
EOF

# Create settings.yml with JSON API enabled
cat > searxng/settings.yml << 'EOF'
use_default_settings: true
server:
  secret_key: "change-me-to-random-string"
  bind_address: "0.0.0.0"
  port: 8080
search:
  safe_search: 0
  autocomplete: "google"
  default_lang: "en"
  formats:
    - html
    - json
EOF

# Start SearXNG
docker compose up -d

Configuration

Set the SearXNG URL (defaults to http://localhost:8080):

export SEARXNG_URL="http://localhost:8080"

Usage Examples

Basic Search

curl "http://localhost:8080/search?q=your+query&format=json" | jq '.results[:5]'

Search with Categories

# General web search
curl "http://localhost:8080/search?q=query&categories=general&format=json"

# Images
curl "http://localhost:8080/search?q=query&categories=images&format=json"

# News
curl "http://localhost:8080/search?q=query&categories=news&format=json"

# Videos
curl "http://localhost:8080/search?q=query&categories=videos&format=json"

# IT/Tech documentation
curl "http://localhost:8080/search?q=query&categories=it&format=json"

# Science/Academic
curl "http://localhost:8080/search?q=query&categories=science&format=json"

Search with Language/Region

curl "http://localhost:8080/search?q=query&language=en-US&format=json"
curl "http://localhost:8080/search?q=query&language=de-DE&format=json"

Paginated Results

# Page 2 (results 11-20)
curl "http://localhost:8080/search?q=query&pageno=2&format=json"

Response Format

Each result includes:

  • title - Result title
  • url - Link to the result
  • content - Snippet/description
  • engines - Array of search engines that returned this result
  • score - Relevance score (higher = better)
  • category - Result category

Shell Function

Add to your .zshrc or .bashrc:

searxng() {
  local query="$*"
  local url="${SEARXNG_URL:-http://localhost:8080}"
  curl -s "${url}/search?q=$(echo "$query" | sed 's/ /+/g')&format=json" | \
    jq -r '.results[:10][] | "[\(.score | floor)] \(.title)\n    \(.url)\n    \(.content // "No description")\n"'
}

Usage: searxng how to make sourdough bread

Docker Management

# Start
cd ~/Projects/searxng && docker compose up -d

# Stop
docker compose down

# View logs
docker compose logs -f searxng

# Restart
docker compose restart

Troubleshooting

Container won't start:

docker compose logs searxng

JSON format not working: Ensure formats: [html, json] is in your settings.yml

No results: Some engines may be rate-limited. Check logs for errors.

Why SearXNG?

  • Privacy: No tracking, no ads, no data collection
  • Aggregation: Combines results from 70+ search engines
  • Self-hosted: Your data stays on your machine
  • API: JSON output for automation
  • Free: No API keys or rate limits

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,1421,171

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

969933

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

683829

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

691549

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

797540

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

697374

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.