CSV File Tools
Inspect, filter, sort and edit CSV text with four free tools. No account or API key required.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"csv-file-tools": {
"url": "https://csvfile.tools/api/csv/mcp"
}
}
}遠端端點
https://csvfile.tools/api/csv/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢inspect_csv(csv, delimiter, previewRows)
Return record, maximum column and cell counts with up to 20 preview records. Preserve ragged and empty records; never infer types or a delimiter.
輸入結構描述
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"maxLength": 262144,
"description": "Complete UTF-8 CSV text, up to 256 KiB. All cells remain strings; formulas are never evaluated."
},
"delimiter": {
"default": ",",
"description": "Explicit delimiter; no delimiter inference.",
"type": "string",
"enum": [
",",
"\t",
";",
"|"
]
},
"previewRows": {
"default": 20,
"type": "integer",
"minimum": 0,
"maximum": 20
}
},
"required": [
"csv"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢filter_csv_rows(csv, delimiter, column, value, hasHeader)
Keep data records whose explicit zero-based column equals an exact string. Header defaults to preserved. Reject missing target columns; preserve empty and ragged records otherwise.
輸入結構描述
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"maxLength": 262144,
"description": "Complete UTF-8 CSV text, up to 256 KiB. All cells remain strings; formulas are never evaluated."
},
"delimiter": {
"default": ",",
"description": "Explicit delimiter; no delimiter inference.",
"type": "string",
"enum": [
",",
"\t",
";",
"|"
]
},
"column": {
"type": "integer",
"minimum": 0,
"maximum": 199,
"description": "Zero-based column index. Every data record must contain this column."
},
"value": {
"type": "string",
"maxLength": 262144
},
"hasHeader": {
"default": true,
"description": "Preserve the first record as a header.",
"type": "boolean"
}
},
"required": [
"csv",
"column",
"value"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢sort_csv_rows(csv, delimiter, column, direction, hasHeader)
Stably sort data records by an explicit zero-based column using literal code-unit string order, asc or desc. Header defaults to preserved. No numeric, date or locale inference. Reject missing target columns.
輸入結構描述
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"maxLength": 262144,
"description": "Complete UTF-8 CSV text, up to 256 KiB. All cells remain strings; formulas are never evaluated."
},
"delimiter": {
"default": ",",
"description": "Explicit delimiter; no delimiter inference.",
"type": "string",
"enum": [
",",
"\t",
";",
"|"
]
},
"column": {
"type": "integer",
"minimum": 0,
"maximum": 199,
"description": "Zero-based column index. Every data record must contain this column."
},
"direction": {
"default": "asc",
"type": "string",
"enum": [
"asc",
"desc"
]
},
"hasHeader": {
"default": true,
"description": "Preserve the first record as a header.",
"type": "boolean"
}
},
"required": [
"csv",
"column"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢edit_csv_cells(csv, delimiter, edits)
Apply up to 1,000 explicit edits to existing cells only. Zero-based row indices include the header. Duplicate coordinates apply in input order. Return complete CSV with literal string values; never evaluate formulas.
輸入結構描述
{
"type": "object",
"properties": {
"csv": {
"type": "string",
"maxLength": 262144,
"description": "Complete UTF-8 CSV text, up to 256 KiB. All cells remain strings; formulas are never evaluated."
},
"delimiter": {
"default": ",",
"description": "Explicit delimiter; no delimiter inference.",
"type": "string",
"enum": [
",",
"\t",
";",
"|"
]
},
"edits": {
"maxItems": 1000,
"type": "array",
"items": {
"type": "object",
"properties": {
"row": {
"type": "integer",
"minimum": 0,
"maximum": 49999
},
"column": {
"type": "integer",
"minimum": 0,
"maximum": 199,
"description": "Zero-based column index. Every data record must contain this column."
},
"value": {
"type": "string",
"maxLength": 262144
}
},
"required": [
"row",
"column",
"value"
],
"additionalProperties": false
}
}
},
"required": [
"csv",
"edits"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}社群
證據