smart-searcher-mcp
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"smart-searcher": {
"args": [
"mcp-smart-searcher"
],
"command": "uvx"
}
}
}
该服务需要配置环境变量:GITHUB_TOKEN、PROXY_URL、TAVILY_API_KEY、USE_PROXY
可用工具 (2 个)
该服务在 MCP 协议中暴露的工具,AI 可按需调用
web_search 3 个参数 需填 1 项
Search the web using one or more search engines simultaneously. Args: query: Search query string (non-empty) engines: Search engines to use (duckduckgo, baidu, juejin, github, github_code, tavily) limit: Maximum number of results per engine (1-50, default 10) Returns: Formatted search results from all specified engines
必填参数:query
fetch_web_content 3 个参数 需填 1 项
Fetch and extract text content from any public URL. Args: url: Public HTTP/HTTPS URL to fetch prompt: Optional hint for what to extract. When provided, the content is filtered to prioritize paragraphs most relevant to the prompt keywords. Useful for AI agents to focus on specific content (e.g., "extract code examples only", "summarize the main argument"). max_chars: Maximum characters to return (default 30000) Returns: Extracted text content from the webpage, optionally filtered by prompt
必填参数:url
服务介绍
MCP Smart Searcher
MCP Smart Searcher 是一个用于在多云提供商环境中搜索资源的工具。它支持多种云服务提供商,如 AWS、GCP 和 Azure。
安装
bash
pip install mcp-smart-searcher
使用方法
基本用法
python
from mcp_smart_searcher import MCPClient
client = MCPClient(provider='aws', region='us-east-1')
resources = client.search(query='ec2 instances')
print(resources)
高级用法
搜索特定标签的资源
python
from mcp_smart_searcher import MCPClient
client = MCPClient(provider='gcp', project='my-project')
resources = client.search(query='instances with tag:environment=production')
print(resources)
搜索多个区域的资源
python
from mcp_smart_searcher import MCPClient
client = MCPClient(provider='azure', subscription_id='12345678-1234-1234-1234-1234567890ab')
resources = client.search(query='virtual machines in regions:westus,eastus')
print(resources)
支持的云服务提供商
- AWS
- GCP
- Azure
文档
更多详细文档请参阅 官方文档。
贡献
欢迎贡献代码!请参阅 贡献指南 了解如何参与。
许可证
MCP Smart Searcher 使用 MIT 许可证发布。详情请参阅 LICENSE 文件。