
Connects Claude to Google Sheets via the Pipeworx gateway with five core operations: read ranges, write to specific cells, append rows, inspect spreadsheet structure, and create new spreadsheets. You get the standard CRUD operations you'd expect, plus a sheets_get_spreadsheet tool to explore tabs and properties before manipulating data. Runs over streamable HTTP instead of stdio, and includes an ask_pipeworx wrapper that lets you query in natural language instead of calling tools directly. Useful if you're building workflows that need to read from or write to Google Sheets without managing the API directly. Part of Pipeworx's larger gateway covering 673+ data sources.
Google Sheets MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
sheets_read | Read data from a Google Sheet range. Specify sheet name and range (e.g., 'A1:C10'). Returns rows as arrays of cell values. |
sheets_write | Write data to a Google Sheet range, overwriting existing values. Specify sheet name, range (e.g., 'A1:C10'), and row data. |
sheets_append | Append new rows to the end of a Google Sheet table. Specify sheet name and row data to add. |
sheets_get_spreadsheet | Explore a spreadsheet's structure. Returns title, sheet/tab names, and properties. Use before reading or writing data. |
sheets_create | Create a new Google Spreadsheet. Optionally set title and initial sheet names. Returns spreadsheet ID and sharing URL. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"google_sheets": {
"url": "https://gateway.pipeworx.io/google_sheets/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/google_sheets/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Google_sheets data" })
The gateway picks the right tool and fills the arguments automatically.
MIT