Connect Google Sheets to AI agents over MCP (with Stepper Skill Sets)

Let your AI agent read, add and update Google Sheets rows through a Stepper Skill Set, limited to the actions you choose.

A Skill Set is a toolkit you build in Stepper: you connect your apps, pick which actions an agent may call, and Stepper serves them as one MCP endpoint. The agent never sees your Google Sheets password or API keys, and every call is logged.

Last checked:

What you can let an agent do in Google Sheets

These are the Google Sheets actions you can add to a Skill Set. They're the same actions Stepper workflows use, listed on Stepper's Google Sheets page. You choose which ones the agent gets.

For example, you could ask

  • Look up the row for Harbour Pottery in the Wholesale sheet and tell me their last order date.
  • Add a row to the Expenses worksheet: kiln repair, 12 March, paid by card.
  • Create Spreadsheet Column Create a new column in a specific spreadsheet.
  • Create Spreadsheet Row Creates a new spreadsheet row in a specific spreadsheet.
  • Create Spreadsheet Row at Top Creates a new spreadsheet row at the top of a spreadsheet (after the header row).
  • Clear Spreadsheet Row(s) Clears the contents of the selected row(s) while keeping the row(s) intact in the spreadsheet.
  • Copy Worksheet Creates a new worksheet by copying an existing worksheet.
  • Create Sheet Creates a new sheet
  • Create Worksheet Creates a new worksheet in a Google Sheet.
  • Delete Spreadsheet Row(s) Deletes the selected row(s) from the spreadsheet. This action removes the row(s) and all associated data.
  • Lookup Spreadsheet Rows Find up to 500 rows based on a column and value as line items.
  • Find Worksheet Finds a worksheet by title.
  • Format Spreadsheet Row Format a row in a specific spreadsheet.
  • Get Many Spreadsheet Rows Return up to 1,500 rows as a single JSON value or as line items.
  • Lookup Spreadsheet Row Find a specific spreadsheet row based on a column and value. If found, it returns the entire row.
  • Update Spreadsheet Row(s) Update one or more rows in a specific spreadsheet.

Set it up in 5 steps

You need a Stepper account, a Google Sheets account, and an AI client that supports remote MCP servers, such as ChatGPT, Claude, Cursor or VS Code. Your own agent works too, using a Skill Set token.

  1. Connect Google Sheets to Stepper

    In Stepper, connect your Google Sheets account. Use an account that can do what you want the agent to do, and no more.

  2. Create a Skill Set

    Go to Skill Sets in Stepper, create a Skill Set for this agent, and use Add Entry to add your Google Sheets connection.

  3. Restrict the actions

    Choose only the Google Sheets actions the agent needs. An entry with no actions chosen allows every Google Sheets action, so a short list is safer. To pin a value, such as one channel, table or calendar, hardcode that parameter so the agent can't change it.

  4. Add the Skill Sets server to your AI client

    Add this URL as a remote MCP server:

    https://mcp.stepper.io/skill-sets/mcp

    Then sign in to Stepper when your client asks. On the Stepper screen that follows, pick the Skill Set this agent should use. To switch to a different Skill Set later, remove the server and connect again.

    Chat apps (ChatGPT, Claude and others): add it as a custom connector or app, wherever your client lists remote MCP servers.

    Code editors (Cursor, Windsurf and others that use an mcpServers config):

    {
      "mcpServers": {
        "stepper": {
          "url": "https://mcp.stepper.io/skill-sets/mcp"
        }
      }
    }

    Your own agent or script: generate a Skill Set token in Stepper and send it as Authorization: Bearer sst_….

  5. Test it

    Ask the agent what it can do (it checks the Skill Set's list of skills) and make sure only the Google Sheets actions you chose appear. Then run one request using the lowest-risk action you allowed, such as a lookup or a draft, and check the call in the Skill Set's call log in Stepper.

Google Sheets's own MCP server, and when to use it instead

Google documents a separate MCP server for each Google Workspace product, including Sheets. They're currently in Google's Workspace Developer Preview Program, and you set them up through a Google Cloud project. Read Google's Workspace MCP guide for setup.

Use Google's servers when you're in the Developer Preview Program, you're comfortable setting up a Google Cloud project, and you want to connect to Google directly.

A Skill Set fits when the agent needs Google Sheets alongside other apps through one endpoint, or when you want to choose exactly which actions it can call, lock parameter values, and check a log of every call.

Guardrails

An agent can misread a request, and some Google Sheets actions change or remove real data. Set these up before you rely on it.

Scope

Lock the spreadsheet and worksheet so the agent can't write anywhere else. Leave Delete Spreadsheet Row(s) and Clear Spreadsheet Row(s) off unless it needs them.

Use a separate Skill Set for each agent or role, so each one gets only its own actions and tokens.

Audit

Every skill call is logged with the tool name, status, how it authenticated, and when. Call logs are kept for 30 days and are visible in Stepper, so you can check what the agent did in Google Sheets.

Revoke

Revoke a Skill Set token from Stepper to cut off a script or client straight away. To stop an agent using one action, remove it from the Skill Set; that applies from the agent's next call, with no need to reconnect. You can also remove the server from your AI client.

Add with care: Clear Spreadsheet Row(s), Delete Spreadsheet Row(s).

Connect other apps to AI agents over MCP:

Google Sheets is a trademark of its owner. Stepper isn't affiliated with or endorsed by Google Sheets; its name is used here only to describe the integration.