AI Skill Hub 强烈推荐:SearXNG MCP 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
SearXNG MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
SearXNG MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/TadMSTR/searxng-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"searxng-mcp": {
"command": "npx",
"args": ["-y", "searxng-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 SearXNG MCP 执行以下任务... Claude: [自动调用 SearXNG MCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"searxng_mcp": {
"command": "npx",
"args": ["-y", "searxng-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
An MCP server for private web search via a self-hosted SearXNG instance. Results are reranked by a local ML model, full-page content is fetched via Firecrawl, and an optional Ollama instance provides query expansion and LLM-synthesized summaries.
Designed for use with Claude Code and LibreChat agents that need web search without sending queries to a third-party search API.
Built with Claude Code using the multi-agent workflow from homelab-agent — the same platform that uses searxng-mcp in production for AI-assisted research.
/v1/rerank endpoint (optional)qwen3:4b and/or qwen3:14b pulled (optional, for query expansion and summarization)CI runs pnpm audit on every push. The lockfile (pnpm-lock.yaml) is committed for reproducible, auditable builds.
kiwix-serve serves ZIM archives over HTTP. Download the required ZIM files and run kiwix-serve with --nodatealiases (-z) so book names are stable:
kiwix-serve --port 8292 --nodatealiases /path/to/zims/
Required ZIM files for each supported host: - Wikipedia: wikipedia_en_all_mini (or maxi) - Stack Overflow: stackoverflow.com_en_all - Arch Wiki: archlinux_en_all_maxi
ZIM files can be downloaded from library.kiwix.org.
All service URLs are configurable via environment variables.
| Variable | Default | Description |
|---|---|---|
SEARXNG_URL | http://localhost:8081 | SearXNG instance URL |
FIRECRAWL_URL | http://localhost:3002 | Firecrawl instance URL |
RERANKER_URL | http://localhost:8787 | Reranker instance URL |
FIRECRAWL_API_KEY | placeholder-local | Firecrawl API key (if required) |
GITHUB_TOKEN | *(unset)* | GitHub personal access token — increases rate limit from 60 to 5,000 req/hour |
OLLAMA_URL | *(unset)* | Ollama API base URL — required for expand and search_and_summarize |
OLLAMA_API_KEY | *(unset)* | Bearer token for authenticated Ollama proxies — adds Authorization: Bearer <key> header when set |
OLLAMA_EXPAND_MODEL | qwen3:4b | Model used by query expansion (expand parameter). Override without rebuilding. |
OLLAMA_SUMMARIZE_MODEL | qwen3:14b | Model used by search_and_summarize. Override without rebuilding. |
VALKEY_URL | redis://localhost:6381 | Redis-compatible URL — enables result caching. Server degrades gracefully if unavailable. |
CACHE_TTL_SECONDS | 3600 | Search result cache TTL in seconds |
FETCH_CACHE_TTL_SECONDS | 86400 | Fetched page cache TTL in seconds |
EXPAND_QUERIES | false | Set to true to enable query expansion globally |
CRAWL4AI_URL | *(unset)* | Crawl4AI instance URL — enables second-tier fetch fallback when Firecrawl fails |
CRAWL4AI_API_TOKEN | *(unset)* | Optional Bearer token for Crawl4AI instances with API token protection |
WAYBACK_ENABLED | false | Set to true to enable Wayback Machine tier-4 fallback — fetches archived snapshots when all three tiers fail |
KIWIX_URL | *(unset)* | kiwix-serve base URL (e.g. http://localhost:8292) — enables Kiwix fast path for Wikipedia, Stack Overflow, and Arch Wiki. Feature is disabled and zero-overhead when unset. |
{
"mcpServers": {
"searxng": {
"command": "npx",
"args": ["-y", "@tadmstr/searxng-mcp"],
"env": {
"SEARXNG_URL": "http://localhost:8081",
"FIRECRAWL_URL": "http://localhost:3002",
"RERANKER_URL": "http://localhost:8787",
"OLLAMA_URL": "http://localhost:11434",
"VALKEY_URL": "redis://localhost:6379",
"CRAWL4AI_URL": "http://localhost:11235"
}
}
}
}
高质量的开源MCP工具,支持私有网页搜索和重排序
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,SearXNG MCP 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | searxng-mcp |
| Topics | mcpsearxngtypescriptreranker |
| GitHub | https://github.com/TadMSTR/searxng-mcp |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-05 · 更新时间:2026-06-05 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端