Import Check: Validate & Clean CSV
Validate and prepare CSV; reconcile two tables with exact keys and full findings. Fixed free demos.
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": {
"import-check": {
"url": "https://import-check-production.up.railway.app/mcp"
}
}
}遠端端點
https://import-check-production.up.railway.app/mcpstreamable-httphttps://check.orvel.dev/mcpstreamable-http它能做什麼
工具清單
工具（10）
🟢get_csv_example
Return a fixed synthetic CSV and its column schema. Free, no key or quota. Copy the structure, then supply your own CSV to validate_csv.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_csv_exampleArguments"
}🟢view_csv_demo
Validate the fixed example with the current engine. Free and no arguments; demonstrates duplicate, email, amount and date findings. Custom files require validate_csv and paid access.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "view_csv_demoArguments"
}🟢get_csv_usage
Read remaining operations and expiry for the API key supplied in the Authorization header. Does not consume credit.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_csv_usageArguments"
}🟢get_table_example
Return fixed synthetic left/right tables and a reusable join recipe. No arguments, key or credit. Copy the structure for reconcile_tables; mode controls which unmatched rows appear in output.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_table_exampleArguments"
}🟢view_table_demo
Join the bundled fixed tables and show changed and unmatched records. No arguments, key or credit. This cannot process custom data; use reconcile_tables with a paid key for your files.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "view_table_demoArguments"
}🟢inspect_table(table, request_id)
Profile a CSV or explicit string table before writing a recipe. Return empty, distinct and duplicate-value counts per column and complete formula warnings; no schema or business validity is inferred. Supply CSV OR columns/rows, never both. JSON numbers must be encoded as strings so identifiers keep leading zeros. One paid operation; no content retained. Reuse request_id only for identical input.
輸入結構描述
{
"type": "object",
"properties": {
"table": {
"$ref": "#/$defs/TableInput"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Id"
}
},
"required": [
"table"
],
"$defs": {
"TableInput": {
"additionalProperties": false,
"properties": {
"csv_text": {
"anyOf": [
{
"maxLength": 1000000,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "CSV including headers; no paths or URLs.",
"title": "Csv Text"
},
"delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Delimiter",
"type": "string"
},
"columns": {
"anyOf": [
{
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 100,
"minItems": 1,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Columns"
},
"rows": {
"anyOf": [
{
"items": {
"items": {
"maxLength": 10000,
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"maxItems": 10000,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Rows"
}
},
"title": "TableInput",
"type": "object"
}
},
"title": "inspect_tableArguments"
}⚪prepare_table(table, recipe, request_id)
Select, rename, derive and convert columns using a caller-owned version-1 recipe. Rules reference original input headers; output follows recipe order and omitted columns are listed. All input rows remain. Any failed conversion returns valid=false, all findings and csv_text=null, never a partially transformed file. No arithmetic, arbitrary code, schema inference or destination writes. One completed report costs one operation, including valid=false. Use reconcile_tables for two-file matching.
輸入結構描述
{
"type": "object",
"properties": {
"table": {
"$ref": "#/$defs/TableInput"
},
"recipe": {
"$ref": "#/$defs/Recipe"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Id"
}
},
"required": [
"table",
"recipe"
],
"$defs": {
"OutputColumn": {
"additionalProperties": false,
"properties": {
"name": {
"maxLength": 100,
"minLength": 1,
"title": "Name",
"type": "string"
},
"source": {
"anyOf": [
{
"maxLength": 100,
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
},
"literal": {
"anyOf": [
{
"maxLength": 10000,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Literal"
},
"concat": {
"anyOf": [
{
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Concat"
},
"separator": {
"default": "",
"maxLength": 100,
"title": "Separator",
"type": "string"
},
"actions": {
"description": "Ordered rules. Dates explicitly use DD/MM/YYYY or MM/DD/YYYY; failed conversions block the output.",
"items": {
"enum": [
"trim",
"lowercase",
"uppercase",
"decimal_comma",
"date_dmy",
"date_mdy"
],
"type": "string"
},
"maxItems": 10,
"title": "Actions",
"type": "array"
}
},
"required": [
"name"
],
"title": "OutputColumn",
"type": "object"
},
"Recipe": {
"additionalProperties": false,
"properties": {
"version": {
"const": 1,
"default": 1,
"title": "Version",
"type": "integer"
},
"columns": {
"description": "Explicit output order; unselected input columns are omitted and reported.",
"items": {
"$ref": "#/$defs/OutputColumn"
},
"maxItems": 100,
"minItems": 1,
"title": "Columns",
"type": "array"
},
"output_delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Output Delimiter",
"type": "string"
},
"spreadsheet_safe": {
"default": false,
"title": "Spreadsheet Safe",
"type": "boolean"
}
},
"required": [
"columns"
],
"title": "Recipe",
"type": "object"
},
"TableInput": {
"additionalProperties": false,
"properties": {
"csv_text": {
"anyOf": [
{
"maxLength": 1000000,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "CSV including headers; no paths or URLs.",
"title": "Csv Text"
},
"delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Delimiter",
"type": "string"
},
"columns": {
"anyOf": [
{
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 100,
"minItems": 1,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Columns"
},
"rows": {
"anyOf": [
{
"items": {
"items": {
"maxLength": 10000,
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"maxItems": 10000,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Rows"
}
},
"title": "TableInput",
"type": "object"
}
},
"title": "prepare_tableArguments"
}⚪reconcile_tables(left, right, recipe, request_id)
Join two bounded tables using exact string or composite keys. Both sides must have non-empty unique keys: duplicates block the entire output, including many-to-many matches. Choose left, inner or full retention explicitly; unmatched records are reported even if excluded. Optional compare fields flag changed values without resolving them. Output includes row lineage; missing-side fields are empty strings. No trimming, fuzzy matching or destination writes. Combined inputs share 1 MB/10,000 records/250,000 cells. One completed report costs one operation; reuse request_id for identical retries. Full findings or an uncharged size error, never silent truncation.
輸入結構描述
{
"type": "object",
"properties": {
"left": {
"$ref": "#/$defs/TableInput"
},
"right": {
"$ref": "#/$defs/TableInput"
},
"recipe": {
"$ref": "#/$defs/JoinRecipe"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Id"
}
},
"required": [
"left",
"right",
"recipe"
],
"$defs": {
"JoinColumn": {
"additionalProperties": false,
"properties": {
"name": {
"maxLength": 100,
"minLength": 1,
"title": "Name",
"type": "string"
},
"side": {
"enum": [
"left",
"right"
],
"title": "Side",
"type": "string"
},
"column": {
"maxLength": 100,
"minLength": 1,
"title": "Column",
"type": "string"
}
},
"required": [
"name",
"side",
"column"
],
"title": "JoinColumn",
"type": "object"
},
"JoinRecipe": {
"additionalProperties": false,
"properties": {
"version": {
"const": 1,
"default": 1,
"title": "Version",
"type": "integer"
},
"keys": {
"description": "Exact string composite key. Empty or duplicate keys on either side block output.",
"items": {
"$ref": "#/$defs/KeyPair"
},
"maxItems": 10,
"minItems": 1,
"title": "Keys",
"type": "array"
},
"mode": {
"description": "Explicit row-retention choice. Unmatched rows are always reported, including those excluded from output.",
"enum": [
"left",
"inner",
"full"
],
"title": "Mode",
"type": "string"
},
"columns": {
"items": {
"$ref": "#/$defs/JoinColumn"
},
"maxItems": 100,
"minItems": 1,
"title": "Columns",
"type": "array"
},
"compare": {
"description": "Optional paired fields; unequal matched values produce value_changed warnings, not automatic resolution.",
"items": {
"$ref": "#/$defs/KeyPair"
},
"maxItems": 100,
"title": "Compare",
"type": "array"
},
"output_delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Output Delimiter",
"type": "string"
},
"spreadsheet_safe": {
"default": false,
"title": "Spreadsheet Safe",
"type": "boolean"
}
},
"required": [
"keys",
"mode",
"columns"
],
"title": "JoinRecipe",
"type": "object"
},
"KeyPair": {
"additionalProperties": false,
"properties": {
"left": {
"maxLength": 100,
"minLength": 1,
"title": "Left",
"type": "string"
},
"right": {
"maxLength": 100,
"minLength": 1,
"title": "Right",
"type": "string"
}
},
"required": [
"left",
"right"
],
"title": "KeyPair",
"type": "object"
},
"TableInput": {
"additionalProperties": false,
"properties": {
"csv_text": {
"anyOf": [
{
"maxLength": 1000000,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "CSV including headers; no paths or URLs.",
"title": "Csv Text"
},
"delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Delimiter",
"type": "string"
},
"columns": {
"anyOf": [
{
"items": {
"maxLength": 100,
"minLength": 1,
"type": "string"
},
"maxItems": 100,
"minItems": 1,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Columns"
},
"rows": {
"anyOf": [
{
"items": {
"items": {
"maxLength": 10000,
"type": "string"
},
"maxItems": 100,
"type": "array"
},
"maxItems": 10000,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Rows"
}
},
"title": "TableInput",
"type": "object"
}
},
"title": "reconcile_tablesArguments"
}🟢validate_csv(csv_text, schema, delimiter, request_id)
Check a CSV against your explicit schema; return all issue counts and at most 200 detailed findings. Headers match exactly; required=false permits empty cells, not missing headers. Unique compares raw non-empty strings. Dates use YYYY-MM-DD, decimals use a dot without grouping, booleans use true/false. A valid=false report is a completed paid operation, not a tool failure. No values are changed; use clean_csv for explicit transformations. Validity covers only the supplied rules, not destination-system or business correctness.
輸入結構描述
{
"type": "object",
"properties": {
"csv_text": {
"description": "CSV text including header. UTF-8, at most 1 MB; no file paths or URLs.",
"title": "Csv Text",
"type": "string"
},
"schema": {
"$ref": "#/$defs/CsvSchema"
},
"delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Delimiter",
"type": "string"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional 8–128 character retry key. Reuse only for identical arguments; changed data requires a new key.",
"title": "Request Id"
}
},
"required": [
"csv_text",
"schema"
],
"$defs": {
"Column": {
"additionalProperties": false,
"properties": {
"name": {
"description": "Exact, case-sensitive header after any cleanup rename.",
"maxLength": 100,
"minLength": 1,
"title": "Name",
"type": "string"
},
"type": {
"default": "string",
"enum": [
"string",
"integer",
"decimal",
"boolean",
"date",
"email"
],
"title": "Type",
"type": "string"
},
"required": {
"default": true,
"description": "Reject an empty value. Every declared header must exist regardless.",
"title": "Required",
"type": "boolean"
},
"unique": {
"default": false,
"description": "Require non-empty raw strings to be unique within this column.",
"title": "Unique",
"type": "boolean"
},
"choices": {
"anyOf": [
{
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional exact allowed strings, checked before type conversion.",
"title": "Choices"
},
"minimum": {
"anyOf": [
{
"maxLength": 100,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive numeric bound, as a decimal string. Numeric columns only.",
"title": "Minimum"
},
"maximum": {
"anyOf": [
{
"maxLength": 100,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive numeric bound, as a decimal string. Numeric columns only.",
"title": "Maximum"
},
"max_length": {
"default": 10000,
"maximum": 10000,
"minimum": 1,
"title": "Max Length",
"type": "integer"
}
},
"required": [
"name"
],
"title": "Column",
"type": "object"
},
"CsvSchema": {
"additionalProperties": false,
"properties": {
"columns": {
"items": {
"$ref": "#/$defs/Column"
},
"maxItems": 100,
"minItems": 1,
"title": "Columns",
"type": "array"
},
"allow_extra_columns": {
"default": false,
"title": "Allow Extra Columns",
"type": "boolean"
}
},
"required": [
"columns"
],
"title": "CsvSchema",
"type": "object"
}
},
"title": "validate_csvArguments"
}🟢clean_csv(csv_text, schema, cleanup, delimiter, request_id)
Apply only requested column renames and transformations, then validate the output against schema. Cleanup column names refer to the original headers; schema names refer to the renamed output. Transformations run in listed order. decimal_comma changes only plain numbers such as 12,50; ambiguous grouping stays unchanged. No records or columns are removed. Returned csv_text is UTF-8-compatible with CRLF record endings. One paid operation includes cleanup and validation. Spreadsheet-safe escaping is opt-in and may make numeric negative cells fail numeric validation; inspect the final report before import.
輸入結構描述
{
"type": "object",
"properties": {
"csv_text": {
"title": "Csv Text",
"type": "string"
},
"schema": {
"$ref": "#/$defs/CsvSchema"
},
"cleanup": {
"$ref": "#/$defs/Cleanup"
},
"delimiter": {
"default": ",",
"enum": [
",",
";",
"\t",
"|"
],
"title": "Delimiter",
"type": "string"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Id"
}
},
"required": [
"csv_text",
"schema",
"cleanup"
],
"$defs": {
"Change": {
"additionalProperties": false,
"properties": {
"column": {
"description": "Original header before any renaming.",
"maxLength": 100,
"minLength": 1,
"title": "Column",
"type": "string"
},
"action": {
"enum": [
"trim",
"lowercase",
"uppercase",
"decimal_comma"
],
"title": "Action",
"type": "string"
}
},
"required": [
"column",
"action"
],
"title": "Change",
"type": "object"
},
"Cleanup": {
"additionalProperties": false,
"properties": {
"rename": {
"additionalProperties": {
"type": "string"
},
"description": "Original header to new header; simultaneous rename, no dropping columns.",
"title": "Rename",
"type": "object"
},
"changes": {
"description": "Applied in order to explicitly named original columns only.",
"items": {
"$ref": "#/$defs/Change"
},
"maxItems": 100,
"title": "Changes",
"type": "array"
},
"spreadsheet_safe": {
"default": false,
"description": "Prefix cells starting with spreadsheet formula markers with an apostrophe. Output is then revalidated; numeric negatives may fail numeric types.",
"title": "Spreadsheet Safe",
"type": "boolean"
}
},
"title": "Cleanup",
"type": "object"
},
"Column": {
"additionalProperties": false,
"properties": {
"name": {
"description": "Exact, case-sensitive header after any cleanup rename.",
"maxLength": 100,
"minLength": 1,
"title": "Name",
"type": "string"
},
"type": {
"default": "string",
"enum": [
"string",
"integer",
"decimal",
"boolean",
"date",
"email"
],
"title": "Type",
"type": "string"
},
"required": {
"default": true,
"description": "Reject an empty value. Every declared header must exist regardless.",
"title": "Required",
"type": "boolean"
},
"unique": {
"default": false,
"description": "Require non-empty raw strings to be unique within this column.",
"title": "Unique",
"type": "boolean"
},
"choices": {
"anyOf": [
{
"items": {
"type": "string"
},
"maxItems": 100,
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional exact allowed strings, checked before type conversion.",
"title": "Choices"
},
"minimum": {
"anyOf": [
{
"maxLength": 100,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive numeric bound, as a decimal string. Numeric columns only.",
"title": "Minimum"
},
"maximum": {
"anyOf": [
{
"maxLength": 100,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive numeric bound, as a decimal string. Numeric columns only.",
"title": "Maximum"
},
"max_length": {
"default": 10000,
"maximum": 10000,
"minimum": 1,
"title": "Max Length",
"type": "integer"
}
},
"required": [
"name"
],
"title": "Column",
"type": "object"
},
"CsvSchema": {
"additionalProperties": false,
"properties": {
"columns": {
"items": {
"$ref": "#/$defs/Column"
},
"maxItems": 100,
"minItems": 1,
"title": "Columns",
"type": "array"
},
"allow_extra_columns": {
"default": false,
"title": "Allow Extra Columns",
"type": "boolean"
}
},
"required": [
"columns"
],
"title": "CsvSchema",
"type": "object"
}
},
"title": "clean_csvArguments"
}社群
證據