What SearXNG instances can I use?
Popular public instances include `https://searx.be`, `https://search.sapti.me`, `https://searx.tiekoetter.com`, and `https://searx.work`. You can also point to any other SearXNG instance.
@wfkpk
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"searxng": {
"command": "npx",
"args": [
"-y",
"mcp-searxng-scrape"
],
"env": {
"SEARXNG_URL": "https://searx.be"
}
}
}
}Performs a web search using a public or self-hosted SearXNG instance. Ideal for privacy-friendly search queries across multiple engines including news, blogs, academic, and technical sources. Use this for general-purpose web search without any tracking or profiling. Returns raw results as-is from the search aggregator.
Extracts the main article content from a given URL. Best used for cleaning and isolating the readable text from news sites, blog posts, research articles, and other content-heavy pages. Returns structured data including title, body, and optional metadata. Use this when you already have a URL and want the actual text content for summarization, analysis, or storage.
Performs a web search using a SearXNG instance and automatically scrapes the full article content from the top 5 results. Combines search and extraction in a single step—ideal for quickly collecting real content from multiple sources. Best used when you need not just links but the actual readable text for summarization, NLP tasks, or embeddings. Returns full page text, titles, and metadata from relevant results.
An MCP server for privacy-focused web search and article scraping using SearXNG instances. It provides tools for web search, article extraction, and combined search‑and‑scrape workflows.
Install via npx -y mcp-searxng-scrape or build locally with npm install && npm run build. Set the SEARXNG_URL environment variable to a SearXNG instance URL (e.g., https://searx.be) and configure the server in your MCP client’s JSON settings.
searxng_search, scrape_article, searchsearch automatically scrapes the top 5 resultsPopular public instances include `https://searx.be`, `https://search.sapti.me`, `https://searx.tiekoetter.com`, and `https://searx.work`. You can also point to any other SearXNG instance.
It offers three tools: `searxng_search` (web search), `scrape_article` (extract article content), and `search` (search and automatically scrape the top 5 results).
Use the JSON configuration shown in the README, setting `SEARXNG_URL` in the environment. Example for NPX: `{"mcpServers":{"searxng":{"command":"npx","args":["-y","mcp-searxng-scrape"],"env":{"SEARXNG_URL":"https://searx.be"}}}}`.
Node.js and npm are required to build and run the server locally (`npm install`, `npm run build`). The server is executed as a standard MCP stdio process.
No. SearXNG instances used are public, and the server does not require any API keys or authentication tokens.
AI search, X search and web search for AI agents, plus page extraction and X data tools. Bring your own Desearch API key.

Verified Spanish and European case law for Claude, ChatGPT and any MCP client. 4M+ official legal documents (TS, TC, AN, TSJ, TJUE, TEDH, BOE, BORME, Catastro) with ECLI citations, BOE article validity checks, and judici
Software research to help people choose the right tools. SaaS Think Tank publishes software comparisons, reviews and practical resources across categories, with dated findings, source links and clear limits. Current MCP
Search & filter 14M+ USPTO trademark records from an AI agent. This is a trademark MCP server, not a TSDR lookup.
MCP server: resolve a company name, domain or LEI to its GLEIF legal entity for $0.05 via x402 — one tool, spend caps, free terms preview
コメント