mcp-searxng
This MCP server connects to the API of a SearXNG instance so an AI client can search the web. It exposes two tools. `searxng_web_search` takes a query with optional page number, time range (day, month, year), language and safe-search level. `web_url_read` fetches a URL and converts it to markdown, with options to start at a character position, limit length, extract the content under a heading, return paragraph ranges or only the list of headings. URL content is cached with a time-to-live to cut repeated requests.
You must supply a SearXNG instance: the required setting is the `SEARXNG_URL` environment variable (default `http://localhost:8080`). Optional settings cover HTTP Basic Auth for password-protected instances, a custom User-Agent and proxy variables. Run it with `npx -y mcp-searxng`, install it globally with `npm install -g mcp-searxng`, or use the `isokoliuk/mcp-searxng` Docker image. STDIO is the default transport; setting `MCP_HTTP_PORT` turns on an HTTP mode with `/mcp` and `/health` endpoints.
Because it queries your own SearXNG, search is not tied to a commercial search API key, although result quality depends on the engines your instance uses. The README states the MIT license, and the repository was last pushed on 2026-10-12. This review is based on the README and repository data; we have not run it ourselves.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-22
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 16
- Latest release
- v2.7.0 (2026-10-20)
- Open issues
- 0
- Recent issues with at least one comment
- 1/1
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!