MCP Connector

Manipulate Excel Data Without Excel

Manipulate Excel files with AI. Create, read, update workbooks, worksheets, data, charts, and pivot tables without needing Excel installed.

Works with excel

Maintainer of this project? Claim this page to edit the listing.


91
Spark score
out of 100
Updated 3 months ago
Version 0.1.8
Models
universal

Add to Favorites

Why it matters

Empower your AI agents to directly interact with Excel files, enabling the creation, reading, and modification of workbooks and sheets without requiring Microsoft Excel to be installed.

Outcomes

What it gets done

01

Create, read, and update Excel workbooks and sheets programmatically.

02

Perform data manipulation including formulas, formatting, and charts.

03

Automate data validation and integrity checks within Excel files.

04

Manage Excel tables, charts, and pivot tables via an AI agent.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-excel | bash

Capabilities

Tools your agent gets

create_workbook

Create a new Excel workbook with specified sheets and data.

read_workbook

Read and retrieve data from an existing Excel workbook.

update_workbook

Modify and update data in an existing Excel workbook.

create_sheet

Create a new sheet within an Excel workbook.

copy_sheet

Copy an existing sheet within or between Excel workbooks.

rename_sheet

Rename an existing sheet in an Excel workbook.

delete_sheet

Delete a sheet from an Excel workbook.

add_formula

Add formulas to cells in an Excel workbook.

+6 tools

Overview

Excel MCP Server

The Excel MCP Server is a Model Context Protocol (MCP) server designed for AI agents. It enables the creation, reading, and modification of Excel workbooks and worksheets without requiring Microsoft Excel to be installed. The server supports advanced features like data manipulation with formulas, formatting, chart creation, and pivot tables. Use this server when your AI agent needs to interact with Excel files for tasks such as data entry, report generation, data analysis, or automating spreadsheet workflows. It is particularly useful in environments where installing Microsoft Excel is not feasible or desired.

What it does

The big job is to enable AI agents to interact with and manage Excel data programmatically. The small job is to provide a robust MCP server that allows an AI client to perform various Excel operations, such as creating, reading, updating workbooks and worksheets, manipulating data with formulas and formatting, generating charts, and creating pivot tables, all without requiring Microsoft Excel to be installed on the machine.

For local use, you can start the server with the stdio transport:

uvx excel-mcp-server stdio

Or configure it in your MCP client like this:

{
   "mcpServers": {
      "excel": {
         "command": "uvx",
         "args": ["excel-mcp-server", "stdio"]
      }
   }
}
Source README

Excel MCP Server Logo

PyPI version
Total Downloads
License: MIT
smithery badge
Install MCP Server

A Model Context Protocol (MCP) server that lets you manipulate Excel files without needing Microsoft Excel installed. Create, read, and modify Excel workbooks with your AI agent.

Features

  • πŸ“Š Excel Operations: Create, read, update workbooks and worksheets
  • πŸ“ˆ Data Manipulation: Formulas, formatting, charts, pivot tables, and Excel tables
  • πŸ” Data Validation: Built-in validation for ranges, formulas, and data integrity
  • 🎨 Formatting: Font styling, colors, borders, alignment, and conditional formatting
  • πŸ“‹ Table Operations: Create and manage Excel tables with custom styling
  • πŸ“Š Chart Creation: Generate various chart types (line, bar, pie, scatter, etc.)
  • πŸ”„ Pivot Tables: Create dynamic pivot tables for data analysis
  • πŸ”§ Sheet Management: Copy, rename, delete worksheets with ease
  • πŸ”Œ Triple transport support: stdio, SSE (deprecated), and streamable HTTP
  • 🌐 Remote & Local: Works both locally and as a remote service

Usage

The server supports three transport methods:

1. Stdio Transport (for local use)

uvx excel-mcp-server stdio
{
   "mcpServers": {
      "excel": {
         "command": "uvx",
         "args": ["excel-mcp-server", "stdio"]
      }
   }
}

2. SSE Transport (Server-Sent Events - Deprecated)

uvx excel-mcp-server sse

SSE transport connection:

{
   "mcpServers": {
      "excel": {
         "url": "http://localhost:8000/sse",
      }
   }
}

3. Streamable HTTP Transport (Recommended for remote connections)

uvx excel-mcp-server streamable-http

Streamable HTTP transport connection:

{
   "mcpServers": {
      "excel": {
         "url": "http://localhost:8000/mcp",
      }
   }
}

Environment Variables & File Path Handling

SSE and Streamable HTTP Transports

When running the server with the SSE or Streamable HTTP protocols, you must set the EXCEL_FILES_PATH environment variable on the server side. This variable tells the server where to read and write Excel files.

  • If not set, it defaults to ./excel_files.
  • With these transports, tool filepath values must be relative to that directory (e.g. reports/q1.xlsx); absolute paths and directory traversal are rejected.

You can also set the FASTMCP_PORT environment variable to control the port the server listens on (default is 8017 if not set).

  • Example (Windows PowerShell):
    $env:EXCEL_FILES_PATH="E:\MyExcelFiles"
    $env:FASTMCP_PORT="8007"
    uvx excel-mcp-server streamable-http
    
  • Example (Linux/macOS):
    EXCEL_FILES_PATH=/path/to/excel_files FASTMCP_PORT=8007 uvx excel-mcp-server streamable-http
    

Stdio Transport

When using the stdio protocol, the file path is provided with each tool call, so you do not need to set EXCEL_FILES_PATH on the server. The server will use the path sent by the client for each operation.

Available Tools

The server provides a comprehensive set of Excel manipulation tools. See TOOLS.md for complete documentation of all available tools.

Star History

Star History Chart

FAQ

Common questions

Discussion

Questions & comments Β· 0

Sign In Sign in to leave a comment.