mcp-searxng

MCP.Pizza Chef: ihor-sokoliuk

SearXNG is a search front end that asks many engines at once. Point this at an instance you run or trust, and your assistant can search the web and then read the pages it finds. It handles news and article searches, time-range and language filters, and pulls the readable text out of a web page or a PDF. There is no paid search account to buy, though you do have to supply the address of a SearXNG site.

Web/Research

Use This MCP server To

Search the web without handing queries to a big search company Read a long article and get the key points back Pull the text out of a PDF I found online Check what was published on a topic in the last week Gather sources and see where each claim came from Compare results from several search engines at once

README

🔍 SearXNG MCP Server

Privacy-respecting web search for AI assistants — use an operator-controlled or trusted SearXNG instance with Claude, Cursor, and more.

GitHub Stars npm version npm downloads Docker Pulls License: MIT OpenSSF Scorecard OpenSSF Best Practices mcp-searxng MCP server GitHub MCP Registry

An MCP server that integrates the SearXNG API, giving AI assistants web search capabilities.

✨ Featured in the GitHub MCP Registry.

Quick Start

Add to your MCP client configuration (e.g. claude_desktop_config.json):

mcp-searxng FAQ

Do I have to pay for a search account?
No. There is no paid search key involved; you only need the address of a SearXNG site.
Which apps does it work in?
Claude Desktop, Claude Code, Codex CLI, Cursor, VS Code, Windsurf, Cline and OpenCode all have written recipes.
Can I use this to research a topic and get real sources?
Yes — it searches, opens the pages and returns the text, so every answer can be checked.
Is it actually private?
Only as private as the site you pick. A public SearXNG instance still sees your query; running your own avoids that.
How hard is setup?
You paste a short block of settings into your app and fill in your SearXNG address.
Can it read a page, not just find it?
Yes. It converts a page to plain text, including a bounded amount of text from PDFs.