tableski is answering right now. Last checked 2 min ago. Last commit 31 Oct 2026.
Every spreadsheet is a table: Excel, CSV, Parquet and JSON as SQL tables for AI agents.
Today is the operative word: we check tableski every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add tableski --transport http https://mcp.tableski.io/
https://mcp.tableski.io/
[mcp_servers.tableski]
url = "https://mcp.tableski.io/"
{
"mcpServers": {
"tableski": {
"url": "https://mcp.tableski.io/"
}
}
}
{
"servers": {
"tableski": {
"type": "http",
"url": "https://mcp.tableski.io/"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.tableski.io/ | streamable-http | sign-in | 400 ms | 2 min ago |
Local data runtime for AI agents: query CSV, Excel, Parquet and JSON files with DuckDB SQL.
Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
Spreadsheet MCP for any agent: reads xlsx/xls/ods/csv, SQL, cleaning, formulas, safe edits
Read-only WHOOP v2 data for MCP clients, with local SQLite cache and CSV/JSONL/Parquet exports.
SQLite-authoritative entity database with an async Google Sheets projection for AI agents.
MCP server for spreadsheet files (.xlsx, .csv, .ods) - cell-level ops + DuckDB SQL engine.
Your coding agent answers with dashboards: charts and tables from read-only SQL, Excel and CSV.
Answers built from our own checks of this server.