MCP server implementation for awesome SearXNG search aggregator
SaferSkills independently audited searxng-mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
To provide a powerful, privacy-focused search capability using a local SearXNG instance. This skill enables agents to perform web searches, explore available engines, and refine results using categories and time ranges.
searxng_searchPerform a web search through the SearXNG backend.
Arguments:
query (required): The search terms.categories (optional): Comma-separated list (e.g., news,it). Default: general.engines (optional): Comma-separated list of engines to use.language (optional): Search language (e.g., en-US).pageno (optional): Page number for results.time_range (optional): Filter results by day, month, or year.response_format (optional): Choose between markdown or json.searxng_get_infoRetrieve diagnostic information about the SearXNG instance.
Returns:
categories="news" to improve relevance.searxng_get_info to verify the server status and connection URL.time_range="day" for breaking news or recent software updates.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.