Categories › Data & Databases › Files, spreadsheets, CSV & PDFs
Messy spreadsheets in, clean checkable tables out. Every result carries its arithmetic proof.
Remote server: your requests and data go to ainetcafe.com. Claude Code: claude mcp add --transport http netcafe-tables https://ainetcafe.com/mcp/table?s=registry · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
what_can_you_do — Describe a task in plain language (any language) and get back exactly which tools on this server do it, with ready-to-run example calls — incsv_to_qbo — Convert a transaction CSV into a .qbo / OFX bank-feed file that QuickBooks and similar accounting software import directly. Needs date, descdiff_tables — Matches rows across two CSVs on a key column and reports three things: keys only in A, keys only in B, and keys in both whose other columns clean_table — Tidies a spreadsheet export: removes duplicate rows, trims whitespace (half-width and full-width — Chinese exports are full of ), unifies thmerge_tables — Combines up to 20 CSVs into a single table. Headers do not have to match: columns are unioned and a file missing a column contributes blanksreconcile_ledger — Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amounfix_csv_encoding — Detect the real encoding of a CSV (GB18030, Shift-JIS, Windows-1252…), repair mojibake (UTF-8 that was read as Latin-1, e.g. "é"), and re-eread_xlsx — Read an Excel .xlsx workbook (by URL) into rows — every sheet, or one you name. Returns cell values (not formula text), dates as YYYY-MM-DD write_xlsx — Build an Excel .xlsx file from rows (CSV text or JSON arrays), optionally several sheets at once. Numbers are written as real numbers so thematch_transactions — Match bank statement lines to ledger/invoice entries when there is NO shared key — by amount, date window, reference numbers found inside frdedupe_entities — Find records in a supplier/customer/store list that are probably the SAME entity under different names — "北京星辰科技有限公司" vs "星辰科技(北京)" — by crocsv_to_md_table — CSV (text or URL) → GitHub-flavoured Markdown table.csv_to_chart — CSV (first column = labels, second = values) → chart PNG in one call.csv_to_json — CSV (text or URL) → JSON array of objects (first row = keys). Returns a .json file.json_to_csv — JSON array of objects → CSV file. Flattens keys, quotes fields containing commas.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.