Google Sheets
Read and write Google Sheets: manage spreadsheets, sheets, rows and cells.
About
Google Sheets ships in the w6w first-party pack. It declares 12 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.google-sheets- Version
- 0.2.2
- Author
- w6w
- Licence
- MIT
- Categories
- Spreadsheets · Productivity
Overview
Google Sheets reads and writes spreadsheet data from a workflow — appending new rows, updating existing ranges, or using an append-or-update action that decides between the two based on a key column, which is the pattern most sync workflows actually need rather than always inserting a new row.
Sheet and spreadsheet structure is manageable too: sheets can be created, listed, cleared and deleted, columns and rows can be deleted individually, and whole spreadsheets can be created and deleted, so a workflow can provision or tear down structure as part of its own process rather than assuming it already exists.
A fit for logging workflow output into a spreadsheet as it runs, syncing a sheet with data from another system, or reading a range back to drive a later step’s logic.
Build with Google Sheets
Three routes to the same 12 actions. The Workflow tab is generated from Google Sheets's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
Append or Update Row
sheet-append-or-update Upsert rows by matching on a column value (append if new, update if it exists).
Create Spreadsheet
spreadsheet-create Create a new Google spreadsheet (optionally with initial sheet tabs).
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Google Sheets's real ids.
{
"manifestVersion": "2",
"name": "google-sheets-example",
"steps": [
{
"id": "list-sheets",
"uses": {
"app": "io.w6w.google-sheets",
"action": "list-sheets",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"spreadsheetId": "<spreadsheetId>"
}
}
]
}Here are some of the things you can do
-
List Sheets
readlist-sheets -
Append Row
performsheet-append -
Append or Update Row
performsheet-append-or-update -
Clear
performsheet-clear -
Create Sheet
performsheet-create
+7 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Google Sheets, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Google Sheets. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "sheet-append",
payload: {
spreadsheetId: "<value>",
range: "<value>",
values: "<value>",
// valueInputOption: "<value>",
// insertDataOption: "<value>",
// includeValuesInResponse: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action sheet-append --payload '{"spreadsheetId":"<value>","range":"<value>","values":"<value>"}'Give an AI agent Google Sheets — without giving it Google Sheets's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.google-sheets#list-sheets",
"input": {
"spreadsheetId": "<spreadsheetId>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Google Sheets connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Google Sheets's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Google Sheets itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Google Sheets declares its own checks, so its health is a property of the app rather than something the host guesses at.
Google Sheets platform status
Open incidents for Google Sheets on the Google Workspace Status Dashboard. Unauthenticated and unsigned.