well-016-datacleanup
CSV cleanup: dates, emails, phones, dedupe. x402 $0.005 USDC, Base. As is, no warranty.
我该使用它吗
质量与安全性
B
发现（1）
- LOWTool 'data-cleanup' doesn't follow camelCase/snake_case在 data-cleanup 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~683token 数（工具定义）
~6.4 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 0.53%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"data-cleanup": {
"url": "https://well-016-datacleanup.rainmaker-wells.workers.dev/mcp"
}
}
}远程端点
https://well-016-datacleanup.rainmaker-wells.workers.dev/mcpstreamable-http它能做什么
工具清单
工具（1）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢data-cleanup(url, csv, has_header, trim_whitespace, key_columns, ...)
Clean a CSV ($0.005 USDC): give an https url or inline csv (max 1 MB / 20k rows). Trims whitespace, optional case rules, dates to ISO 8601, lowercases emails, normalizes phone digits, merges or flags exact + fuzzy duplicate rows on key_columns. Returns cleaned CSV text + JSON report (rows in/out, dupes, columns changed). Deterministic, no AI. As is, no warranty. Nothing stored. As is, no warranty. Nothing stored.
输入模式
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of a CSV (max 1 MB).",
"type": "string"
},
"csv": {
"description": "Inline CSV text instead of url (max 1 MB).",
"type": "string"
},
"has_header": {
"description": "First row is a header (default true).",
"type": "boolean"
},
"trim_whitespace": {
"description": "Trim and collapse whitespace in every cell (default true).",
"type": "boolean"
},
"key_columns": {
"description": "Columns used to detect duplicates (default all).",
"maxItems": 200,
"type": "array",
"items": {
"type": "string"
}
},
"dedupe": {
"description": "merge (default) keeps first row and fills its blanks; flag adds _duplicate_of_row; none.",
"type": "string",
"enum": [
"merge",
"flag",
"none"
]
},
"fuzzy": {
"description": "Also match near-duplicates (case/punctuation/accents, small typos). Default true.",
"type": "boolean"
},
"fuzzy_threshold": {
"description": "Similarity 0.5-1 for typo matches (default 0.92; 1 = normalized-equal only).",
"type": "number"
},
"date_columns": {
"description": "Columns to convert to ISO 8601 (default auto).",
"anyOf": [
{
"maxItems": 200,
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "string",
"enum": [
"auto",
"none"
]
}
]
},
"date_order": {
"description": "Order for ambiguous numeric dates (default mdy).",
"type": "string",
"enum": [
"mdy",
"dmy"
]
},
"email_columns": {
"description": "Email columns to lowercase (default auto).",
"anyOf": [
{
"maxItems": 200,
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "string",
"enum": [
"auto",
"none"
]
}
]
},
"phone_columns": {
"description": "Phone columns (default auto by header name).",
"anyOf": [
{
"maxItems": 200,
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "string",
"enum": [
"auto",
"none"
]
}
]
},
"phone_format": {
"description": "digits (default) or e164.",
"type": "string",
"enum": [
"digits",
"e164"
]
},
"default_country_code": {
"description": "Country code for e164 when missing (default 1).",
"type": "string"
},
"case_rules": {
"description": "Map column -> lower | upper | title.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string",
"enum": [
"lower",
"upper",
"title"
]
}
},
"max_groups": {
"description": "Max duplicate groups listed in report (default 50, max 500).",
"type": "number"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据
最近观测
已验证未记录版本1 个工具