How do I install the Searxng Search skill?

Run npx skillmds@latest add ocean326/searxng-search in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Searxng Search safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Searxng Search?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Searxng Search free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Searxng Search?

ocean326 (@ocean326) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Searxng Search by ocean326 — Agent Skill

Name: Searxng Search
Author: ocean326

Searxng Search

Use for web search when you need more than simple lookups AND want a free, unlimited solution. Priority: native websearch (simple) → searxng-search (comprehensive, free) → tavily-search (advanced features). Use when: user wants comprehensive results, mentions "free", "unlimited", "local", "no API key", "SearXNG", or searxng-docker-tavily-adapter stack is running. Falls back to tavily-search if advanced features needed (topic filtering, time ranges).

ocean326 Updated Sep 17, 2026

File contents

searxng search

Free, unlimited web search via local SearXNG. No API key required.

Prerequisites

Requires searxng-docker-tavily-adapter running locally.

# Check if running
curl -s http://localhost:8000/health

If not running, ask user for permission to set up:

# Clone and configure (with user permission)
git clone https://github.com/vakovalskii/searxng-docker-tavily-adapter
cd searxng-docker-tavily-adapter
cp config.example.yaml config.yaml
# Generate secret key and update config.yaml
python -c "import secrets; print(secrets.token_urlsafe(32))"
docker compose up -d

Or start existing stack: docker compose up -d

When to use

Need web search without API keys or limits
User mentions "free", "no API key", "local", "private"
Privacy-focused (local deployment)
Drop-in Tavily replacement for Python code

When NOT to use

Need Tavily's AI-powered research synthesis → use tavily-research
Need advanced search features (topic filtering, time ranges) → use tavily-search
Docker unavailable and user won't start it → use tavily-search

Quick start

curl -X POST "http://localhost:8000/search" \
  -H "Content-Type: application/json" \
  -d '{"query": "your query", "max_results": 5}'

Options

Option	Description
`query`	Search query (required)
`max_results`	Max results 1-20 (default: 10)
`include_raw_content`	Include full page text (default: false)

Response

{
  "query": "search query",
  "results": [{"url": "...", "title": "...", "content": "...", "score": 0.9}],
  "response_time": 1.23
}

Tips

Without raw_content: ~1-2s, snippets only
With raw_content: ~3-5s, full page text (up to 2500 chars)
No API key needed — completely free

Python (drop-in Tavily replacement)

from tavily import TavilyClient
client = TavilyClient(api_key="ignored", base_url="http://localhost:8000")
response = client.search(query="your query", max_results=5)

---name: searxng-searchdescription: Use for web search when you need more than simple lookups AND want a free, unlimited solution. Priority: native websearch (simple) → searxng-search (comprehensive, free) → tavily-search (advanced features). Use when: user wants comprehensive results, mentions "free", "unlimited", "local", "no API key", "SearXNG", or searxng-docker-tavily-adapter stack is running. Falls back to tavily-search if advanced features needed (topic filtering, time ranges).---# searxng searchFree, unlimited web search via local SearXNG. No API key required.## PrerequisitesRequires [searxng-docker-tavily-adapter](https://github.com/vakovalskii/searxng-docker-tavily-adapter) running locally.```bash# Check if runningcurl -s http://localhost:8000/health```If not running, ask user for permission to set up:```bash# Clone and configure (with user permission)git clone https://github.com/vakovalskii/searxng-docker-tavily-adaptercd searxng-docker-tavily-adaptercp config.example.yaml config.yaml# Generate secret key and update config.yamlpython -c "import secrets; print(secrets.token_urlsafe(32))"docker compose up -d```Or start existing stack: `docker compose up -d`## When to use- Need web search without API keys or limits- User mentions "free", "no API key", "local", "private"- Privacy-focused (local deployment)- Drop-in Tavily replacement for Python code## When NOT to use- Need Tavily's AI-powered research synthesis → use tavily-research- Need advanced search features (topic filtering, time ranges) → use tavily-search- Docker unavailable and user won't start it → use tavily-search## Quick start```bashcurl -X POST "http://localhost:8000/search" \ -H "Content-Type: application/json" \ -d '{"query": "your query", "max_results": 5}'```## Options| Option | Description ||--------|-------------|| `query` | Search query (required) || `max_results` | Max results 1-20 (default: 10) || `include_raw_content` | Include full page text (default: false) |## Response```json{ "query": "search query", "results": [{"url": "...", "title": "...", "content": "...", "score": 0.9}], "response_time": 1.23}```## Tips- **Without raw_content**: ~1-2s, snippets only- **With raw_content**: ~3-5s, full page text (up to 2500 chars)- **No API key needed** — completely free## Python (drop-in Tavily replacement)```pythonfrom tavily import TavilyClientclient = TavilyClient(api_key="ignored", base_url="http://localhost:8000")response = client.search(query="your query", max_results=5)```## See also- [searxng-extract](../searxng-extract/SKILL.md) — extract from URLs- [tavily-search](../tavily-search/SKILL.md) — original Tavily (requires API key)

Frequently asked questions