This server enables real-time interaction with live Microsoft Excel instances on macOS, allowing AI agents to read, write, and manipulate spreadsheet data and execute macros directly — locally, with no API keys required.
List open workbooks — view all currently open Excel files, including names, paths, and sheet counts
Get sheet names — retrieve all sheet names from a specific or active workbook
Read a cell range — read a rectangular range (e.g. A1:D20) as a 2D array, with optional auto-expansion to contiguous data
Write a range — write a 2D array of data starting from a specified cell; changes appear instantly in Excel
Write a single cell — write a value, number, or formula (e.g. =SUM(A1:A10)) to one cell
Read a single cell — read the value and formula of a specific cell
Open a workbook — open an Excel file from a given path, launching Excel if needed
Save a workbook — save the active or specified workbook in place or to a new path
Run a VBA macro — execute an existing VBA macro in the active workbook, optionally passing arguments
Get current selection — retrieve the address, values, and sheet of the user's currently selected range
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@excel-live-mac read the current selection in the active sheet"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Live Excel MCP server for macOS — interact with running Excel instances in real time.
Unlike file-based tools (openpyxl) that work on saved files offline, this server talks to the live Excel app via the xlwings AppleScript bridge. Changes appear instantly in the spreadsheet you're looking at.
10 tools for reading, writing, and interacting with open Excel workbooks
Real-time updates — write data and watch it appear in Excel immediately
Formula support — write Excel formulas that calculate live
VBA macro execution — trigger existing macros from your AI agent
Selection awareness — read what the user currently has highlighted
Zero config — no API keys, no network, runs entirely local
Related MCP server: SheetForge MCP
macOS (AppleScript bridge — not available on Windows/Linux)
Microsoft Excel installed
Python 3.10+
Import from GitHub in the Kiro Powers panel:
https://github.com/dcol3/excel-live-macuvx --from git+https://github.com/dcol3/excel-live-mac excel-live-macOr add to your MCP config:
{
"mcpServers": {
"excel-live-mac": {
"command": "uvx",
"args": ["--from", "git+https://github.com/dcol3/excel-live-mac", "excel-live-mac"],
"disabled": false
}
}
}pip install excel-live-mac
excel-live-macOn first use, macOS will prompt you to allow your terminal to control Microsoft Excel.
Go to System Settings → Privacy & Security → Automation and ensure your terminal/IDE has permission to control Excel.
Tool | Description |
| List all open workbooks (name, path, sheets) |
| Get sheet names from a workbook |
| Read a cell range as a 2D array |
| Write a 2D array (appears instantly) |
| Write a value or formula to one cell |
| Read one cell's value and formula |
| Open a file in Excel |
| Save the workbook |
| Execute a VBA macro |
| Get the current selection |
Report generation — AI builds formatted spreadsheets while you watch
Financial modeling — populate budgets, forecasts, and scenario tables live
Data entry automation — read from databases, write directly into open workbooks
Interactive analysis — AI reads your current selection, computes, writes results back
This repo includes a kiro_power/ directory with POWER.md, mcp.json, and steering files for use as a Kiro Power. When installed as a Power, Kiro's agent automatically knows when and how to use these tools based on keyword activation.
MIT
Get info about the currently selected range in Excel (address, values, sheet).
Inputs: no named parameters.
Get all sheet names from an open workbook.
Inputs: workbook.
List all currently open workbooks in Excel. Shows name, path, and sheet count.
Inputs: no named parameters.
Open a workbook file in Excel. Launches Excel if not running.
Inputs: file_path (required).
Read the value of a single cell.
Inputs: cell (required), workbook, sheet.
Read a range from an open workbook. Returns cell values as a 2D array.
Inputs: range (required), workbook, sheet, expand.
Run a VBA macro in the active workbook. Macro must already exist in the workbook.
Inputs: macro (required), workbook, args.
Save the specified (or active) workbook.
Inputs: workbook, path.
Write a single value to a specific cell. Change appears immediately.
Inputs: cell (required), value (required), workbook, sheet.
Write a 2D array of data to a range in an open workbook. Changes appear immediately in Excel.
Inputs: range (required), data (required), workbook, sheet.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Each tool targets a distinct action: reading/writing cells vs ranges, listing sheets, managing workbooks, running macros. No overlapping purposes; descriptions clearly differentiate them.
All tools share the 'excel_' prefix and follow a consistent verb_noun pattern (e.g., read_cell, write_range, open_workbook), making it easy to infer functionality.
With 10 tools, the server covers essential Excel operations without being bloated or sparse. Each tool serves a clear need.
Basic CRUD on cells/ranges and workbook listing/saving are covered, but missing features like creating workbooks, managing sheets, closing workbooks, or formatting leave notable gaps for full automation.
Trading MCP server for AI agents, with live market data, account reads and controlled execution.
Hosted MCP server for MT4 and MT5: read accounts, prices and candles, and place or close orders.
MCP server for Financial Modeling Prep API with 250+ financial data tools
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
