Excel logo

Excel

Community
negokaz

A Model Context Protocol (MCP) server that reads and writes MS Excel data

Publishernegokaz
Repositoryexcel-mcp-server
LanguageGo
Forks
113
Stars
951
Available tools
6
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    Excel exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 6 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    951 stars and 113 forks from the linked repository.

Excel MCP Server

NPM Version smithery badge

A Model Context Protocol (MCP) server that reads and writes MS Excel data.

Features

  • Read/Write text values
  • Read/Write formulas
  • Create new sheets

🪟Windows only:

  • Live editing
  • Capture screen image from a sheet

For more details, see the tools section.

Requirements

  • Node.js 20.x or later

Supported file formats

  • xlsx (Excel book)
  • xlsm (Excel macro-enabled book)
  • xltx (Excel template)
  • xltm (Excel macro-enabled template)

Installation

Installing via NPM

excel-mcp-server is automatically installed by adding the following configuration to the MCP servers configuration.

For Windows:

json
{
    "mcpServers": {
        "excel": {
            "command": "cmd",
            "args": ["/c", "npx", "--yes", "@negokaz/excel-mcp-server"],
            "env": {
                "EXCEL_MCP_PAGING_CELLS_LIMIT": "4000"
            }
        }
    }
}

For other platforms:

json
{
    "mcpServers": {
        "excel": {
            "command": "npx",
            "args": ["--yes", "@negokaz/excel-mcp-server"],
            "env": {
                "EXCEL_MCP_PAGING_CELLS_LIMIT": "4000"
            }
        }
    }
}

Installing via Smithery

To install Excel MCP Server for Claude Desktop automatically via Smithery:

bash
npx -y @smithery/cli install @negokaz/excel-mcp-server --client claude

excel_describe_sheets

List all sheet information of specified Excel file.

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file

excel_read_sheet

Read values from Excel sheet with pagination.

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • sheetName
    • Sheet name in the Excel file
  • range
    • Range of cells to read in the Excel sheet (e.g., "A1:C10"). [default: first paging range]
  • showFormula
    • Show formula instead of value [default: false]
  • showStyle
    • Show style information for cells [default: false]

excel_screen_capture

[Windows only] Take a screenshot of the Excel sheet with pagination.

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • sheetName
    • Sheet name in the Excel file
  • range
    • Range of cells to read in the Excel sheet (e.g., "A1:C10"). [default: first paging range]

excel_write_to_sheet

Write values to the Excel sheet.

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • sheetName
    • Sheet name in the Excel file
  • newSheet
    • Create a new sheet if true, otherwise write to the existing sheet
  • range
    • Range of cells to read in the Excel sheet (e.g., "A1:C10").
  • values
    • Values to write to the Excel sheet. If the value is a formula, it should start with "="

excel_create_table

Create a table in the Excel sheet

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • sheetName
    • Sheet name where the table is created
  • range
    • Range to be a table (e.g., "A1:C10")
  • tableName
    • Table name to be created

excel_copy_sheet

Copy existing sheet to a new sheet

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • srcSheetName
    • Source sheet name in the Excel file
  • dstSheetName
    • Sheet name to be copied

excel_format_range

Format cells in the Excel sheet with style information

Arguments:

  • fileAbsolutePath
    • Absolute path to the Excel file
  • sheetName
    • Sheet name in the Excel file
  • range
    • Range of cells in the Excel sheet (e.g., "A1:C3")
  • styles
    • 2D array of style objects for each cell. If a cell does not change style, use null. The number of items of the array must match the range size.
    • Style object properties:
      • border: Array of border styles (type, color, style)
      • font: Font styling (bold, italic, underline, size, strike, color, vertAlign)
      • fill: Fill/background styling (type, pattern, color, shading)
      • numFmt: Custom number format string
      • decimalPlaces: Number of decimal places (0-30)

You can change the MCP Server behaviors by the following environment variables:

EXCEL_MCP_PAGING_CELLS_LIMIT

The maximum number of cells to read in a single paging operation.
[default: 4000]

License

Copyright (c) 2025 Kazuki Negoro

excel-mcp-server is released under the MIT License

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "excel": {
      "command": "npx",
      "args": [
        "--yes",
        "@negokaz/excel-mcp-server"
      ],
      "env": {
        "EXCEL_MCP_PAGING_CELLS_LIMIT": "4000"
      }
    }
  }
}

Available Tools

  • excel_copy_sheet

    Copy existing sheet to a new sheet

  • excel_create_table

    Create a table in the Excel sheet

  • excel_describe_sheets

    List all sheet information of specified Excel file

  • excel_format_range

    Format cells in the Excel sheet with style information

  • excel_read_sheet

    Read values from Excel sheet with pagination.

  • excel_write_to_sheet

    Write values to the Excel sheet

Use Excel MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Excel is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Excel as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Excel MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "excel": {
      "command": "npx",
      "args": [
        "-y",
        "excel-mcp-server"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Excel MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Excel MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Excel to help me with this task?
Excel
Sure. I read it.
Here is what I found using Excel.

Frequently asked questions

What is the Excel MCP server used for?

Excel is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Excel MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Excel with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Excel MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Excel connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Excel MCP to TypingMind?

Excel runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Excel MCP provide in TypingMind?

Excel exposes 6 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Excel MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Excel requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇