A Model Context Protocol (MCP) server that enables LLMs to leverage SearXNG—a privacy-respecting metasearch engine.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"searxng-mcp-server-rust": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A high-performance Model Context Protocol (MCP) server that enables LLMs to leverage SearXNG—a privacy-respecting metasearch engine. By aggregating results from multiple engines while masking your digital fingerprint, this server provides superior search quality without compromising privacy.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in search
Web and local search using Brave Search API
Production ready MCP server with real-time search, extract, map & crawl.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
MCP server for Firecrawl — search, scrape, and interact with the web. Supports both cloud and self-hosted instances. Features include web search, scraping, page interaction, batch processing, and LLM-powered content analysis.
MCP Security Weekly
Get CVE alerts and security updates for Searxng Mcp Server Rust and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A high-performance Model Context Protocol (MCP) server that enables LLMs to leverage SearXNG—a privacy-respecting metasearch engine. By aggregating results from multiple engines while masking your digital fingerprint, this server provides superior search quality without compromising privacy.
Built with Rust for maximum efficiency and future scalability, the project is designed with a minimal footprint, utilizing Distroless containers to keep the production image extremely small and secure.
Dockerfile and docker-compose.yml for quick deployment alongside a SearXNG instance.Clone the repository:
git clone <repo-url>
cd searxng-mcp-server-rust
Run with Docker Compose:
StdIO Mode (Default):
docker compose up -d
HTTP Mode:
MCP_TRANSPORT=http docker compose up -d
This will start both the SearXNG instance and the MCP server.
The server is configured via environment variables:
| Variable | Description | Default |
|---|---|---|
MCP_TRANSPORT | Transport mode: stdio or http | stdio |
SEARXNG_URL | URL of the SearXNG instance | http://localhost:8080 |
PORT | HTTP port (only used in http mode) | 3000 |
Ideal for connecting to local AI clients (e.g., LM Studio, Claude Desktop).
export MCP_TRANSPORT=stdio
cargo run
Useful for debugging or remote deployments.
export MCP_TRANSPORT=http
cargo run
searxng_searchPerforms a search and returns the top results.
query (string, required): The search query.category (string, optional): Search category (e.g., general, news, science).You can use the MCP Inspector to test the server:
StdIO:
npx @modelcontextprotocol/inspector cargo run
HTTP:
npx @modelcontextprotocol/inspector http://localhost:3000/sse