What is web-search-via-searxng?

A web-search skill that uses SearXNG, a search system that queries several search engines. It helps the coding agent find current information, documentation, images, papers, code and packages.

Use it to look up API documentation, research technical topics, check news, find academic papers, or search for code, packages and media.

It avoids relying on possibly outdated knowledge or searching each source separately. It is useful when an answer needs information from the live web.

web-search-via-searxng — Skill for Claude Code by whw23

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add whw23/searxng_http_mcp --skill web-search-via-searxng

Clone the repo

git clone --depth 1 https://github.com/whw23/searxng_http_mcp

Made for: Claude Code.

Or install searxng-http-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/whw23/searxng_http_mcp/web-search-via-searxng/github.svg)](https://agentmods.dev/skills/whw23/searxng_http_mcp/web-search-via-searxng)

Your own site

<a href="https://agentmods.dev/skills/whw23/searxng_http_mcp/web-search-via-searxng"><img src="https://agentmods.dev/badge/skills/whw23/searxng_http_mcp/web-search-via-searxng/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/whw23/searxng_http_mcp/web-search-via-searxng"><img src="https://agentmods.dev/badge/skills/whw23/searxng_http_mcp/web-search-via-searxng.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,095 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.01095
Opus 5	$0.00025	$0.00548
Sonnet 5	$0.00010	$0.00219
Haiku 4.5	$0.00005	$0.00110

Measured 12d ago against content hash 93348731a6a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

web-search-via-searxng scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/local/skills/web-search-via-searxng/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SearXNG Web Search

Use the configured SearXNG MCP server to search the web.

When to Use

Answering questions that need up-to-date information
Looking up documentation or API references
Researching technical topics
Finding news or current events
Searching for images, videos, academic papers, code, packages

How to Search

Prefer delegating to the web-searcher agent via the Agent tool. The agent handles multi-language parallel search, source credibility verification, cross-validation, iterative deepening, and structured summarization — returning a clean result without polluting your context window with raw JSON. Only call the MCP search tools directly when:

The web-searcher agent is unavailable (e.g., no subagent support)
You need a single quick lookup where spawning an agent is overkill

MCP Tools Reference

When searching directly (without the agent), use these tools:

`search`

Main search tool. Parameters:

query (required): Search terms
categories: Comma-separated category names (e.g., 'general,news,science'). Prefer this over engines — categories leverage multiple engines automatically
language: Language code (e.g., zh, en, ja). Filters results to the specified language
time_range: day, week, month, year
safesearch: 0 (off), 1 (moderate), 2 (strict)
pageno: Starting page number (default 1)
pages: Number of pages to fetch in parallel, 1-5 (default 1). Use 2-3 for comprehensive research
max_results: Maximum results to return (default 10, max 100)
format: compact (default, title/url/content only) or full (includes engines, score, dates)
engines: Comma-separated engine names (e.g., google,arxiv,wikipedia). Only use when you need a specific source

`autocomplete`

Get search query suggestions. Use before searching to discover relevant terms. Best results come from 1-2 meaningful keywords (e.g., "python async"). Single characters return overly broad suggestions; full sentences return none. Makes an external API call to the configured backend (e.g., Bing, Google).

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 95 lines · 50 tokens per session scan A 93348731a6a5

Subscribe to this mod's changes

web-search-via-searxng is a skill published in the GitHub repository whw23/searxng_http_mcp (10 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,095 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens