3.9 KiB
3.9 KiB
Search Tools for Hermes Agent
Current Environment
| Tool | Type | Usage |
|---|---|---|
| web (built-in) | Web Search & Scraping | web_search, web_extract tools |
| session_search | Session history | session_search(query="...") |
| mmx search | MiniMax CLI | mmx search query "关键词" |
Popular Search APIs for AI Agents
| Tool | Best For | Pricing | MCP Server |
|---|---|---|---|
| Tavily Search | AI-native search, structured results | Free tier available | tavily-mcp |
| SerpAPI | Google results scraping | Paid (100 free/month) | serpapi-mcp |
| Brave Search | Privacy-focused, no tracking | Free tier (2000/month) | brave-search-mcp |
| Perplexity API | AI search with citations | Paid | API only |
| Firecrawl | Web scraping + extraction | Free tier | firecrawl-mcp |
| Jina Reader | URL to Markdown conversion | Free tier | API only |
| SearXNG | Self-hosted meta search | Free (self-hosted) | searxng-mcp |
Configuration Examples
Tavily Search (Recommended for AI Agents)
# ~/.hermes/config.yaml
mcp_servers:
tavily:
command: npx
args: ["-y", "tavily-mcp@latest"]
env:
TAVILY_API_KEY: "tvly-xxxxx"
Get API key: https://tavily.com (free tier: 1000 searches/month)
Brave Search
mcp_servers:
brave-search:
command: npx
args: ["-y", "@anthropic/brave-search-mcp@latest"]
env:
BRAVE_API_KEY: "BSAxxxxx"
Get API key: https://brave.com/search/api/ (free tier: 2000 queries/month)
Firecrawl (for Web Scraping)
mcp_servers:
firecrawl:
command: npx
args: ["-y", "firecrawl-mcp"]
env:
FIRECRAWL_API_KEY: "fc-xxxxx"
When to Use Which
| Scenario | Recommended Tool |
|---|---|
| Quick factual lookup | mmx search or built-in web_search |
| Structured data extraction | Tavily Search |
| Google-specific results | SerpAPI |
| Privacy-sensitive search | Brave Search |
| Deep web scraping | Firecrawl |
| Convert page to markdown | Jina Reader |
| Previous conversation context | session_search |
Pitfalls
- mcp_servers: {} is currently empty in this environment
- Tool changes require
/reset(new session) to take effect - Free tiers have rate limits; monitor usage for production use
- Some MCP servers require Node.js (
npxcommand) - mmx search Token Plan 限制：
mmx search query需要 MiniMax Token Plan 支持coding-plan-search模型。报错 "your current token plan not support model" 表示 plan 不含搜索能力，需升级或换替代方案 - 服务器出站网络受限：某些云服务器/容器的出站网络被限制，
urllib报Network is unreachable(errno 101)。此时 curl、Python requests、mimo_search.py 均无法访问外部。排查：curl -s -o /dev/null -w "%{http_code}" https://www.baidu.com - Playwright/Chrome 沙盒问题：服务器上 Chrome 需要
--no-sandbox参数才能启动。Hermes 的 browser 工具可能因沙盒限制失败。排查：检查 Chrome stderr 中是否有 "No usable sandbox" 错误 - mimo_search.py 环境变量：脚本依赖
XIAOMI_API_KEY环境变量，但 Hermes config.yaml 中的 key 不会自动 export。需手动export XIAOMI_API_KEY=...或从 config 提取
搜索降级策略（按优先级）
当用户请求搜索时，按以下顺序尝试：
- mmx search — 最简单，但需 Token Plan 支持
- mimo_search.py — MiMo 原生搜索，需 XIAOMI_API_KEY 环境变量 + 网络可达
- web_search 工具 — Hermes 内置，需 web toolset 启用
- Playwright 浏览器 — 通用兜底，但需 Chrome 可启动
- curl + 搜索引擎 — 最基础，需服务器出站网络可达
全部失败时，告知用户具体失败原因（Token Plan 限制 / 网络不通 / 浏览器沙盒问题），并建议用户在本地自行搜索。