JSON to CSV Skill

Overview

The converter scans every object in `json` and collects the union of their keys in order of first appearance. That list becomes `columns`, so the column order follows the first object that introduced each key. Each object is then written as one row in that column order; a key that is missing, `null` or `undefined` produces an empty cell. Rows are joined with `\n` line endings.

Values are converted with JavaScript string conversion. Numbers and booleans come out as written, an array becomes its items joined by commas, and a nested object becomes the literal text `[object Object]`, so flatten nested structures before sending them. A value is wrapped in double quotes when it contains the `delimiter`, a double quote, a newline or a carriage return, and embedded quotes are doubled, following the usual CSV convention.

`delimiter` defaults to a comma. `include_header` defaults to true; set it to false to get data rows only, while `columns` and `column_count` are still returned. `row_count` is the number of objects in the array. The request must carry a `Content-Length` header and the body may not exceed 512,000 bytes; larger bodies get a 413. An empty array is rejected as a missing parameter.

Live Test JSON to CSV Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as JSONtoCSVSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "JSONtoCSVSkill",
  "arguments": {
    "json": "[{\"name\":\"John\",\"age\":30},{\"name\":\"Jane\",\"age\":25}]"
  }
}

You do not name the tool yourself; the model picks it. Asking about [{"name":"John","age":30},{"name":"Jane","age":25}] in the terms this skill covers is enough for it to reach for JSONtoCSVSkill on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`json`Required	array	The JSON array to convert to CSV (must be array of objects)
`delimiter`Optional	string	The delimiter to use in the CSV `,;\t\|` default ,
`include_header`Optional	boolean	Whether to include column headers in the output (default: true) default true

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "row_count": 2,
    "column_count": 3,
    "columns": [
      "name",
      "age",
      "city"
    ],
    "csv": "name,age,city\nJohn Doe,30,New York\nJane Smith,25,Los Angeles"
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`row_count`	number	`2`	Total number of data rows in the converted CSV output
`column_count`	number	`3`	Total number of columns extracted from JSON object keys
`columns`	array	`["name","age","city"]`	Array of column header names extracted from JSON data
`csv`	string	`name,age,city John Doe,30,New York Jane Smith,25,Los Angeles`	Formatted CSV content with headers and data rows combined

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This skill is not part of VerveKit. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 1 credit each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Data Export: Convert API JSON responses to CSV format for importing into Excel, Google Sheets, or databases
Report Generation: Transform JSON data into CSV reports for business intelligence tools and data analysis
Legacy System Integration: Convert modern JSON APIs to CSV format for compatibility with legacy systems
Data Backup: Export JSON datasets to CSV format for archival and backup purposes

Other ways to use JSON to CSV Skill

Set up JSON to CSV Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →

Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheets →Reference →