mcp-searxng
Enables private web searches within AI workflows without exposing queries to commercial search providers, reducing data leakage risk while maintaining curren…
MCP server that connects Claude, Cursor, or any MCP client to a SearXNG metasearch instance for private web search. Provides web search with pagination, time-range, language, safe-search, and relevance-score filters, plus URL content reading with TTL caching, search suggestions, and automatic failover across multiple SearXNG replicas. Free, self-hosted, no API key — point SEARXNG_URL at your instance.
- Ask Claude to search internal documentation and find specific API endpoints without exposing queries to public search engines
- Generate competitive analysis by searching multiple sources simultaneously for pricing and feature comparisons across vendors
- Find relevant code examples and Stack Overflow solutions while keeping search queries private within your infrastructure
Enables private web searches within AI workflows without exposing queries to commercial search providers, reducing data leakage risk while maintaining current information access for code research and decision-making.
Engineering teams needing to integrate real-time web search into Claude workflows while maintaining data privacy and control over search infrastructure.
https://github.com/ihor-sokoliuk/mcp-searxng
By ihor-sokoliuk
How to Get It
claude mcp add searxng -e SEARXNG_URL=<your-searxng-instance-url> -- npx -y mcp-searxng
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Search internal documentation and find specific API endpoints without exposing queries to public search engines
Trust Signals Auto-scanned
Data & Access
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 942 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 942 GitHub stars; contributors unknown; last commit 0d ago; license MIT.