SearXNG Search
MCP server for SearXNG, privacy-respecting web search with pagination, URL reading
At a glance
Not tested yet- GitHub stars
- 1,377
- Last commit
- 2026-11-17
- Licence
- MIT
- Transport
- stdio
- Auth
- api-key
npx -y mcp-searxng
What it does
SearXNG Search is an MCP server that connects an AI assistant to a SearXNG instance so the assistant can search the web. It does not install SearXNG. You point it at an instance you operate or trust, and it gives the assistant search, query suggestions, instance details and URL reading.
Tools it gives your agent
searxng_web_search: find sources and refine results.searxng_search_suggestions: complete or refine a query.searxng_instance_info: inspect categories, engines and defaults.web_url_read: read a known URL as text or Markdown.
Quick start
You need an existing SearXNG instance with JSON search enabled. Install Node.js 22 or later for NPX and npm installs.
npm install -g mcp-searxng
Reload the client, inspect its MCP tool inventory, then ask it to search for SearXNG documentation. A simple tool call is searxng_web_search with {"query":"SearXNG"}. Discovery alone does not test SearXNG connectivity.
Add this to .mcp.json in your project root (Claude Code) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"mcp-searxng": {
"command": "npx",
"args": [
"-y",
"mcp-searxng"
],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_URL",
"AUTH_USERNAME": "YOUR_AUTH_USERNAME",
"AUTH_PASSWORD": "YOUR_AUTH_PASSWORD"
}
}
}
}Replace each YOUR_ value with your own, and delete the variables you do not use.
Environment variables
SEARXNG_URL: identifies the SearXNG service, not the MCP endpoint. It is the required setting for the default local setup.AUTH_USERNAME: declared by the server. The README does not explain it.AUTH_PASSWORD: declared by the server. The README does not explain it.
Example prompts
- Search the web for SearXNG documentation.
- Suggest completions for my search query about MCP servers.
- Show me which categories and engines this SearXNG instance offers.
- Read this URL and give me the text.
What to watch out for
- You must supply an existing SearXNG instance with JSON search enabled. This project does not install SearXNG.
- Privacy depends on the SearXNG deployment. A public instance receives the query and may log it. SearXNG and this integration do not by themselves provide anonymity.
- URL reading fetches the selected website directly.
- The README points to separate guides for troubleshooting, configuration and deployment limits.
Not tested by tools4agents yet. Read the source repository before you install it.
Similar tools
Firecrawl MCP Server
Crawls, scrapes, and converts dynamic web pages into clean, LLM-ready Markdown or structured JSON data.
Fetch
Retrieves a URL and converts the page to markdown so an agent can read it without burning tokens on raw HTML.
Context7 MCP Server
Injects up-to-date documentation and code examples from official sources directly into AI prompts.
Apify MCP Server
Connects AI agents to the Apify platform to run web scrapers, crawlers, and data extraction actors across 1,000+ websites.