Data Analysis
使用多种统计方法检测数值数据中的异常值，包括IQR、Z-score和修正Z-score
用三种语言从你的代码中调用此工具。
curl -X POST 'https://api.elysiatools.com/zh/api/tools/outlier-detector' \
-H 'Content-Type: application/json' \
-d '{"dataInput":"Enter numerical data separated by delimiter...\n12.5, 15.2, 13.8, 45.6, 18.9, 16.1, 14.7, 17.3, 22.1","delimiter":"comma","customDelimiter":"输入自定义分隔符","detectionMethod":"iqr","sensitivity":1.5,"includeStatistics":true,"outputFormat":"summary"}'以 JSON 形式 POST 提交输入参数。文件类型参数需先单独上传。
POST https://api.elysiatools.com/zh/api/tools/outlier-detector| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| dataInput | textarea | 是 | — |
| delimiter | select | 是 | — |
| customDelimiter | text | 否 | — |
| detectionMethod | select | 是 | — |
| sensitivity | number | 否 | — |
| includeStatistics | checkbox |
将此工具加入你的 Model Context Protocol 服务，让 AI 智能体可以列出并调用它。
将以下内容加入你的 MCP 客户端配置：
{
"mcpServers": {
"elysiatools-outlier-detector": {
"name": "outlier-detector",
"description": "使用多种统计方法检测数值数据中的异常值，包括IQR、Z-score和修正Z-score",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=outlier-detector",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}连接到 SSE 端点后，列出已开放的工具：
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}通过工具 id 调用，参数由其参数表构建：
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "outlier-detector",
"arguments": {
"dataInput": "Enter numerical data separated by delimiter...\n12.5, 15.2, 13.8, 45.6, 18.9, 16.1, 14.7, 17.3, 22.1",
"delimiter": "comma",
"customDelimiter": "输入自定义分隔符",
"detectionMethod": "iqr",
"sensitivity": 1.5,
"includeStatistics": true,
"outputFormat": "summary"
}
}
}有问题或反馈？请联系 [email protected]
| 否 |
| — |
| outputFormat | select | 是 | — |
文本结果
{
"result": "Processed text content",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}