Skip to main content
Glama
Internamaro Apify Data MCP

Internamaro Apify Data MCP

Excel to JSON

excel_to_json
Read-only

Convert Excel .xlsx files from a public URL into JSON rows, or turn JSON/NDJSON files into Excel sheets.

Instructions

Returns one JSON item per spreadsheet row (numbers and dates kept). For a JSON/NDJSON file it returns one item with a download link to the new .xlsx file. Reads an Excel .xlsx file from a public URL (one sheet or all sheets, any header row) and turns its rows into JSON. A JSON or NDJSON file goes the other way, into an Excel sheet. Give at least one of: fileUrl. Runs the Apify Actor ucchiii/excel-to-json on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/excel-to-json.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "excel_to_json"
  }
}

Input Schema

NameRequiredDescriptionDefault
sheetNoExcel to JSON: sheet name (case does not matter). Empty = the first sheet; * = all sheets (each row gets a _sheet field and the .json file is an object keyed by sheet name). JSON to Excel: name of the new sheet (default Data).
fileUrlNoPublic http(s) link to the file, up to 100 MB. An Excel file (.xlsx) becomes JSON; a JSON or NDJSON file becomes Excel.
fileNameNoStart of the output file name, for example 'prices' gives prices.json or prices.xlsx. Empty = taken from the source file name.
headerRowNoExcel to JSON: the row that holds the column names (default 1). Rows above it are skipped. 0 = no header row (columns are named column_1, column_2, ...).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real value beyond that: it names the underlying Actor, states that it runs on the caller's own Apify account with APIFY_TOKEN, and discloses pay-per-event billing. It does not cover failure modes (bad URL, oversized file, malformed sheet) or whether the download link expires.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly four sentences with no filler, but the ordering is backwards: it leads with return values ('Returns one JSON item per spreadsheet row') before stating what the tool does, and the billing/URL sentence is tacked on at the end. Front-loading the conversion purpose would make it scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does carry the return-value burden and does so reasonably: one JSON item per row, numbers and dates preserved, a download link for the .xlsx direction. But it omits what the JSON output looks like structurally (array vs. object, the _sheet field is only in the schema) and says nothing about error behavior for a tool that depends on an external Actor and a remote URL.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented in detail, including sheet semantics, headerRow=0 behavior, and the 100 MB limit. The description only restates 'one sheet or all sheets, any header row' without adding format or edge-case detail, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource in both directions: reads an .xlsx from a public URL and turns rows into JSON, or converts JSON/NDJSON into an Excel sheet. The bidirectional nature is clear, though the description never contrasts itself with any sibling, so an agent must infer that flatten_json or html_to_markdown are not substitutes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by file type ('An Excel file (.xlsx) becomes JSON; a JSON or NDJSON file becomes Excel'), which is genuinely useful routing logic. However there is no explicit when-not guidance, no mention of alternatives for related tasks, and the line 'Give at least one of: fileUrl' conflicts with a schema that marks nothing required, leaving the agent unsure whether a call with no arguments is valid.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.