Allows a language model to read SQLite databases as plain-text MTSV, converting database tables into sheet-separated text for inspection.
Let a language model read a whole multi-sheet spreadsheet as text. The model calls one tool with the path of a file, or a folder of files, on your machine, and Excel, ODS, CSV, JSON, SQLite, Parquet, Arrow and MTSV come back as MTSV: one plain-text file where a tab separates fields, a line break separates records, and a form feed separates sheets.
A language model reads text, so a binary workbook is a dead end —
without pandas or openpyxl in the loop, it cannot see inside an
.xlsx at all. This converts the whole file, every sheet, in one
call, so the model reads a spreadsheet the way it reads any other
text file.
The Python implementation, in an environment of its own:
pipx install text-spreadsheetThen tell your host to launch text-spreadsheet, with no arguments.
Most hosts read a configuration file that maps a name to a command;
some write that file for you from their own command line. It is one
entry, once — after that the tool is in every session.
Released on PyPI as
text-spreadsheet and in
the MCP registry as
io.github.demos-ra/text-spreadsheet.
See python/README.md for the tool, the addresses
and filters it takes, and what it keeps. Its version is the version field of
python/pyproject.toml, and versions follow
Semantic Versioning.
Related MCP server: tablebridge
Path | Contents |
| the entry that lists this server in the MCP registry |
| Python implementation of the server |
Each language folder holds one implementation of the same server. This repository holds no format code: every conversion is MTSV's, and what a spreadsheet holds that MTSV does not is reported as MTSV reports it.
Report a problem or ask a question in the issue tracker. text-spreadsheet is maintained by Demos Ra.
This server cannot be deployed
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
PDF, Word, Excel, CSV, HTML and XML to clean Markdown for LLMs and RAG, with token counts.