Convert and clean tables: CSV, JSON, dedupe, stats. Free.
Scored across 4 tools
Each tool targets a clearly different table operation (cleaning, computing a single column statistic, format conversion, splitting a column), and the descriptions explicitly state what not to use and which alternative to choose. There is no realistic overlap that would cause misselection.
All names use snake_case and are readable, with three following a verb_noun pattern (clean_table, convert_table, split_column). column_stats breaks the pattern by being noun_noun, but the overall convention remains predictable.
Four tools is well-scoped for a focused table-manipulation server, and each tool earns its place without redundancy. The count supports a compact, purpose-built toolkit rather than an overstuffed API.
The surface covers core table preparation, conversion, column splitting, and simple single-column statistics. Common row-level operations like filtering, sorting, or joining tables are absent, but these are minor gaps relative to the stated formatting and cleaning focus.
Clean a table: trim whitespace in cells, drop fully empty rows, and optionally remove duplicate rows; returns the table in the same format with before/after row counts. Use when preparing messy pasted data. Do NOT use to change format; use convert_table.
Inputs: data (required), trim, dedupe, format, +1 more. Returns: text, rows_after, rows_before
Compute one statistic over a single column: sum, avg, min or max (numeric, rounded to 2 dp, blanks ignored), count of non-empty cells, or the sorted distinct values. Use for quick answers like 'total of the price column'. Do NOT use to reshape the table; use split_column or convert_table.
Inputs: op (required), data (required), column (required), format. Returns: op, column, result
Convert a table from CSV, TSV or JSON into CSV, TSV, JSON (array of objects) or a Markdown table. Cell values are kept as text. Use when the user wants the same table in another format. Do NOT use to trim, dedupe or drop rows; use clean_table.
Inputs: data (required), to_format (required), from_format (required). Returns: rows, text, columns
Split one column into several columns on a delimiter (e.g. 'full name' on a space), inserted in place; short rows are padded with empty cells. Returns the table in the same format. Use when one column packs several values. Do NOT use to clean or change format; use clean_table or convert_table.
Inputs: data (required), column (required), delimiter (required), format, +1 more. Returns: text, parts
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Dedupe, flatten and clean messy JSON rows (emails, phones, URLs, HTML) in one call, as JSON or CSV.
Clean, dedupe, join and reconcile CSV/Excel files. Runs on Apify, pay per use.
Messy CSV, JSON, Excel, SPSS/Stata/SAS and PDF tables to typed Parquet; inspect, query, join.
Extract every table from PDFs and scans to Excel, CSV and JSON.
Add one secure layer between your agents and this server.