Text Spreadsheet runs on your own machine — the client starts it, so there is no endpoint to ping. 306 installs a week from pypi.
Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
Today is the operative word: we check Text Spreadsheet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add text-spreadsheet -- uvx text-spreadsheet
{
"mcpServers": {
"text-spreadsheet": {
"args": [
"text-spreadsheet"
],
"command": "uvx"
}
}
}
[mcp_servers.text-spreadsheet]
command = "uvx"
args = ["text-spreadsheet"]
{
"mcpServers": {
"text-spreadsheet": {
"args": [
"text-spreadsheet"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"text-spreadsheet": {
"args": [
"text-spreadsheet"
],
"command": "uvx"
}
}
}
MCP server for spreadsheet files (.xlsx, .csv, .ods) - cell-level ops + DuckDB SQL engine.
Read-only WHOOP v2 data for MCP clients, with local SQLite cache and CSV/JSONL/Parquet exports.
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
Read-only SQL database and plain-text SQL dump schema extraction to compact TOON for MCP clients.
Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases.
Local document queries, saved extraction profiles, spreadsheet SQL, logs and keyed JSON changes.
Query any database in plain English or SQL through a guardrailed, read-only data layer.
Answers built from our own checks of this server.