Google Serper Search Tool

When to Activate

Search-related Keywords

• "search", "look up", "find", "check"
• "research", "investigate", "learn about"
• "inquire", "retrieve"
• "see", "check out"

Specific Scenarios

• Need to get the latest news or information
• Need to verify facts or data
• Need to research a certain technology or concept
• Need to find documents or tutorials
• Need to compare different products or solutions

Example Questions

• "Search the latest AI development trends"
• "Help me search the latest AI development trends"
• "Find the new features of Python 3.13"
• "Research the current status of autonomous driving technology"
• "Check the latest cybersecurity news"
• "Find some tutorials about microservices"

Tools

serper_search

• query

  (required, string): Search keywords

• num

  (optional, number): Number of results to return, default is 5, maximum is 20

• gl

  (optional, string): Country code, default is cn
• Recommended values: cn (China), us (United States), uk (United Kingdom), jp (Japan)

• hl

  (optional, string): Language code, default is zh-CN
• Recommended values: zh-CN (Simplified Chinese), en (English), ja (Japanese)

Best Practices

1. Search Tips

• ✅ "Kimi AI model parameters comparison 2025"
• ✅ "Python 3.13 new features official documentation"
• ❌ "Python" (Too broad, too many results)

2. Add Time Constraints

• ✅ "LangChain latest documentation 2025"
• ✅ "Python 3.13 release date"
• ✅ "AI artificial intelligence news February 2025"

3. Use Exact Search

• ✅ ""machine learning" best practices"
• ✅ ""RAG architecture" implementation"

4. Add Technical Terms

• ✅ "Spring Cloud microservices implementation"
• ✅ "React Hooks useEffect usage"

5. Result Quantity Selection

• Quick query:

  num=3

  (Quickly browse core information)
• In-depth research:

  num=10

  (Comprehensively understand the topic)
• Comprehensive research:

  num=20

  (Maximum depth, wide coverage)

6. Multi-round Search Strategy

// 第一轮：基础概念
serper_search({ query: "微服务架构 概念 优势", num: 5 })

// 第二轮：技术实现
serper_search({ query: "微服务 Spring Cloud Kubernetes", num: 8 })

// 第三轮：最佳实践
serper_search({ query: "微服务 最佳实践 常见问题", num: 10 })

7. Result Handling Principles

• Prioritize authoritative sources: Official documentation, well-known technical blogs, academic papers
• Cross-validation: Compare information from multiple sources
• Focus on timeliness: Prioritize newer content (last 1-2 years)
• Quick screening: Judge relevance through snippets

Example Scenarios

Scenario 1: Technical Research

// 搜索核心概念
serper_search({
  query: "LangChain 核心概念 官方文档 2025",
  num: 5
})

// 如果需要更多细节，继续搜索
serper_search({
  query: "LangChain Agents Chains 使用示例",
  num: 8
})

According to search results, the core concepts of LangChain include:

1. **Chains**: Connect multiple components into a workflow
2. **Agents**: Autonomous decision-making AI agents
3. **Tools**: External capabilities available to LLMs
4. **Memory**: Dialogue context management

📖 Detailed documentation: https://python.langchain.com/

Scenario 2: News Retrieval

serper_search({
  query: "AI artificial intelligence news February 6, 2025",
  num: 10
})

Today's AI Headlines:

1. **OpenAI releases new model**: 30% capability improvement
2. **Google DeepMind**: Breaks new algorithm for protein folding
3. **China AI regulation**: New rules released to promote healthy industry development

🔍 Sources: Major tech media reports

Scenario 3: Product Comparison

// Search comparison reviews
serper_search({
  query: "Kimi ChatGPT comparison review 2025",
  num: 5
})

According to comparison reviews:

| Feature | Kimi | ChatGPT |
|------|------|---------|
| Chinese comprehension | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ |
| Tool calling | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ |
| Response speed | Fast | Medium |

💡 Recommendation: Use Kimi for Chinese tasks, ChatGPT for complex tool calling

Scenario 4: Fact Verification

serper_search({
  query: "Python 4 release plan official statement",
  num: 5
})

Verified:

❌ Python 4 currently has no release plan
✅ Python 3.13 is the latest version (released in October 2024)
✅ Python 3.14 is scheduled to be released in 2025

📊 Information sources: Python official GitHub, PSF announcements

Scenario 5: Quick Lookup

serper_search({
  query: "React Hooks official tutorial Chinese",
  num: 3
})

Recommended tutorials:

1. 📚 **React Official Documentation** (Recommended)
   https://react.dev/learn

2. 🎓 **Ruan Yifeng's React Hooks Tutorial**
   https://www.ruanyifeng.com/blog/2019/09/react-hooks.html

3. 📺 **Bilibili React Hooks Video Tutorial**
   Search for "React Hooks Introduction"

Limitations

• Search result sources: Google, which may be affected by region and personalization
• Access restrictions: Some websites may be blocked or require login
• Result quantity: Maximum 20 results
• Rate limits: The API has call frequency limits; avoid a large number of requests in a short time
• Search quality: Depends on the accuracy and timing of keywords

Configuration

Environment Variable Configuration (Recommended)

~/.openclaw/.env

SERPER_API_KEY=your-api-key-here

Plugin Configuration

apiKey

configSchema

openclaw.plugin.json

Get API Key

Related Tools

• web_search: Brave Search API (alternative solution)
• web_fetch: Get detailed content of a single webpage

Version History

• v1.0 (2026-02-06): Initial version with basic search functionality
  • Supports Google Serper API
  • Provides multilingual search in Chinese and English
  • Integrates with OpenClaw Skill system
• v1.1 (2026-02-11): Optimized description, added trigger keywords
  • Updated description to include trigger keywords
  • Optimized skill activation mechanism

Future Plans

• 📚 serper-scholar: Academic search support
• 🔍 Advanced filtering: Time range, domain filtering
• 📊 Result caching: Improve performance for repeated queries
• 🌍 More regions: Support more countries and languages