实时搜索
tavily-search
by aysun168
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
安装
claude skill add --url https://github.com/openclaw/skills文档
Tavily Search Skill
Use Tavily API for real-time web search and content extraction.
When to Use
✅ USE this skill when:
- "Search the web for [topic]"
- "Find recent information about [subject]"
- "Get current news about [topic]"
- "Research [topic] online"
- "Find up-to-date information"
When NOT to Use
❌ DON'T use this skill when:
- Simple URL fetching → use
web_fetchtool - No API key available → use
web_fetchfor specific URLs - Historical/archival data → use specialized archives
Setup
- Get a Tavily API key from https://tavily.com
- Set the API key in environment or config
Configuration
Set your Tavily API key in one of these ways:
Environment variable:
export TAVILY_API_KEY="your-api-key-here"
OpenClaw config:
Add to your openclaw.json:
{
"tavily": {
"apiKey": "your-api-key-here"
}
}
Usage Examples
Basic Search
# Search for a topic
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "latest AI developments 2026",
"search_depth": "basic",
"max_results": 5
}' | jq .
Research Query
# Get detailed research results
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "climate change impact on agriculture 2026",
"search_depth": "advanced",
"max_results": 10,
"include_answer": true,
"include_images": false
}' | jq .
News Search
# Search for recent news
curl -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "technology news today",
"search_depth": "basic",
"max_results": 5,
"include_raw_content": false
}' | jq .
API Parameters
query: Search query string (required)search_depth: "basic" or "advanced" (default: "basic")max_results: Number of results (1-10, default: 5)include_answer: Include AI-generated answer (true/false)include_images: Include image URLs (true/false)include_raw_content: Include full page content (true/false)
Error Handling
- Check API key is set:
echo $TAVILY_API_KEY - Test connection: Use the basic search example above
- Rate limits: Tavily has usage limits based on your plan
Alternatives
If Tavily API is not available:
- Use
web_fetchfor specific URLs - Use
web_searchwith Kimi API (if configured) - Manual web browsing with
browsertool
相关 MCP 服务
网页抓取
编辑精选by Anthropic
Fetch 是 MCP 官方参考服务器,让 AI 能抓取网页并转为 Markdown 格式。
✎ 这个服务器解决了 AI 直接处理网页内容时格式混乱的问题,适合需要让 Claude 分析在线文档或新闻的开发者。不过作为参考实现,它缺乏生产级的安全配置,你得自己处理反爬虫和隐私风险。
Puppeteer 浏览器控制
编辑精选by Anthropic
Puppeteer 是让 Claude 自动操作浏览器进行网页抓取和测试的 MCP 服务器。
✎ 这个服务器解决了手动编写 Puppeteer 脚本的繁琐问题,适合需要自动化网页交互的开发者,比如抓取动态内容或做端到端测试。不过,作为参考实现,它可能缺少生产级的安全防护,建议在可控环境中使用。
Brave 搜索
编辑精选by Anthropic
Brave Search 是让 Claude 直接调用 Brave 搜索 API 获取实时网络信息的 MCP 服务器。
✎ 如果你想让 AI 助手帮你搜索最新资讯或技术文档,这个工具能绕过传统搜索的限制,直接返回结构化数据。特别适合需要实时信息的开发者,比如查 API 更新或竞品动态。不过它依赖 Brave 的 API 配额,高频使用可能受限。