excel
A Model Context Protocol (MCP) server that reads and writes MS Excel data
claude mcp add --transport stdio negokaz-excel-mcp-server npx --yes @negokaz/excel-mcp-server \ --env EXCEL_MCP_PAGING_CELLS_LIMIT="4000"
How to use
This MCP server provides a bridge for reading and writing data inside Microsoft Excel workbooks. It exposes a set of tools that let you inspect sheets, read and write cell values (with optional formula handling), create tables, copy sheets, and apply styling ranges. The tools are designed to work with a given Excel file path and sheet name, making it convenient to integrate Excel data into your MCP-powered workflows or other automated processes. Supported operations include listing sheets, reading cells with pagination, writing values (including formulas), and formatting ranges. Windows users also have a live editing and screen-capture capability for an active Excel sheet.
To use, configure the MCP server in your environment (see the mcp_config section). Then call the provided tools by name, passing the required arguments such as fileAbsolutePath, sheetName, and range. For example, excel_read_sheet lets you specify a file path, a sheet, and a range to fetch data in pages. If you need to write data, use excel_write_to_sheet with the target file, sheet, range, and the values (prefix formulas with "="). If you need to replicate or reorganize data, excel_copy_sheet and excel_create_table are available. Formatting and styling can be applied via excel_format_range by supplying a 2D array of style objects matching the target range.
How to install
Prerequisites:
- Node.js 20.x or later installed on the host
- Access to run npm/npx commands
Option 1: Installing via NPM (recommended for most environments)
- Ensure your MCP config references the Excel MCP Server (as shown in mcp_config).
- Run the MCP server configuration for Excel by using your MCP manager; the server is installed automatically when the MCP config is loaded.
Example configuration (already shown in this repo):
{
"mcpServers": {
"excel": {
"command": "npx",
"args": ["--yes", "@negokaz/excel-mcp-server"],
"env": {
"EXCEL_MCP_PAGING_CELLS_LIMIT": "4000"
}
}
}
}
Option 2: Installing via Smithery (optional)
- Install via Smithery CLI to use the Excel MCP Server with a client (e.g., Claude):
npx -y @smithery/cli install @negokaz/excel-mcp-server --client claude
- Start or connect to the MCP server as per your Smithery setup.
Prerequisites recap:
- Node.js 20.x+ installed
- Access to npm/npx and the ability to install packages from the MCP registry
- Optional: Smithery CLI if you plan to use the Smithery-based install flow
Additional notes
Environment variable:
- EXCEL_MCP_PAGING_CELLS_LIMIT: Sets the maximum number of cells read in a single paging operation (default 4000). Increase cautiously for very large ranges to avoid excessive memory usage. Common issues:
- Ensure the target Excel file path is accessible from the MCP server process.
- For Windows live editing and screen capture, you must run on Windows; those features are Windows-only.
- When writing formulas, begin with '='; plain text values should be provided without the '=' prefix.
- If using frameworks or containers, verify network and permissions allow the MCP server to spawn or access Excel files as needed.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go