Data Visualization
直观展示中心极限定理：从非正态源分布（均匀、指数、泊松或伯努利）抽样，绘制样本均值的直方图，并叠加预测的正态曲线 N(μ, σ²/n)。对比经验与理论的均值和标准误，观察随样本量增大收敛性增强。
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/central-limit-theorem-demonstrator' \
-H 'Content-Type: application/json' \
-d '{"distribution":"exponential","sampleSize":30,"reps":5000,"bins":40,"seed":42,"precision":3}'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/central-limit-theorem-demonstrator| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| distribution | select | 否 | — |
| sampleSize | number | 是 | Draws per sample mean. Larger n → narrower, more normal sampling distribution. |
| reps | number | 是 | How many sample means to generate (histogram resolution). |
| bins | number | 是 | — |
| seed | number | 否 | Same seed → identical results (reproducible demos). |
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-central-limit-theorem-demonstrator": {
"name": "central-limit-theorem-demonstrator",
"description": "直观展示中心极限定理：从非正态源分布（均匀、指数、泊松或伯努利）抽样，绘制样本均值的直方图，并叠加预测的正态曲线 N(μ, σ²/n)。对比经验与理论的均值和标准误，观察随样本量增大收敛性增强。",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=central-limit-theorem-demonstrator",
"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": "central-limit-theorem-demonstrator",
"arguments": {
"distribution": "exponential",
"sampleSize": 30,
"reps": 5000,
"bins": 40,
"seed": 42,
"precision": 3
}
}
}有问题或反馈？请联系 [email protected]
| precision |
| number |
| 是 |
| — |
HTML 结果
{
"result": "<div>Processed HTML content</div>",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}