excel-mcp
An MCP server for performing Excel file operations including read, write, and manipulation, with enterprise security features and VS Code integration.
README
Excel MCP Server
A Model Context Protocol (MCP) server for Excel operations with enterprise-grade security and clean architecture. Seamlessly integrates with GitHub Copilot, Cline, and other MCP-compatible tools in VS Code.
Features
- Complete Excel Operations: Read, write, and manipulate Excel files (.xlsx, .xls)
- Clean Architecture: Follows Single Responsibility Principle for maintainability
- Enterprise Security: Robust permission system with path restrictions and access control
- VS Code Integration: Works seamlessly with GitHub Copilot and Cline
- TypeScript: Full type safety with modern ES2022+ features
- Zero Deprecated Dependencies: Uses only current, actively maintained libraries
Quick Start
Installation
# Clone the repository
git clone https://github.com/az-coder-123/excel-mcp.git
cd excel-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Copy example environment file
cp .env.example .env
📌 Đã cấu hình sẵn cho Cline
Server đã được cấu hình và kết nối sẵn với Cline! Xem Hướng dẫn cài đặt chi tiết để biết:
✅ Trạng thái hiện tại: Đã kết nối và hoạt động bình thường
- Server đang chạy:
node dist/index.js - Cấu hình Cline:
.cline/mcp_servers.json - File cấu hình đã sẵn sàng sử dụng
Xem ngay: docs/SETUP_GUIDE.md để biết cách sử dụng
Configuration
Edit .env file to customize permissions:
# Restrict access to specific directories
MCP_ALLOWED_PATHS=/home/user/documents,/workspace
# Block sensitive system directories
MCP_DENIED_PATHS=/etc/*,/sys/*,C:\Windows\*
# Set maximum file size (50MB default)
MCP_MAX_FILE_SIZE=52428800
VS Code Integration
For GitHub Copilot
Add to your VS Code settings.json:
{
"github.copilot.chat.experimental.mcpServers": {
"excel-mcp": {
"command": "node",
"args": ["/path/to/excel-mcp/dist/index.js"],
"env": {
"MCP_LOG_LEVEL": "info"
}
}
}
}
For Cline
Add to your Cline MCP configuration file (~/.config/cline/mcp_servers.json):
{
"mcpServers": {
"excel-mcp": {
"command": "node",
"args": ["/path/to/excel-mcp/dist/index.js"],
"env": {
"MCP_LOG_LEVEL": "info"
}
}
}
}
Available Tools
excel_health_check
Check server health, dependencies, and configuration status. This tool is useful for verifying that the MCP server is running correctly and all systems are operational.
{
}
No parameters required
Response Example:
{
"status": "healthy",
"server": {
"name": "excel-mcp",
"version": "1.0.0",
"nodeVersion": "v18.0.0",
"platform": "darwin",
"arch": "arm64",
"uptime": "5m 32s"
},
"dependencies": {
"exceljs": "ok",
"filesystem": "ok",
"memory": "ok",
"memoryUsage": {
"heapUsed": "45MB",
"heapTotal": "64MB",
"rss": "78MB",
"external": "2MB"
}
},
"configuration": {
"logLevel": "info",
"maxFileSize": 52428800,
"maxFileSizeMB": "50MB",
"allowedPathsCount": 0,
"deniedPathsCount": 4,
"allowedExtensions": [".xlsx", ".xls", ".xlsm", ".xlsb"],
"permissions": ["read", "write", "delete"]
},
"tests": {
"permissionChecker": "pass",
"logger": "pass",
"excelOperations": "pass"
},
"responseTime": "45ms",
"timestamp": "2024-03-21T12:34:56.789Z"
}
excel_open_workbook
Open an Excel file for operations.
{
"filePath": "/path/to/file.xlsx"
}
excel_create_workbook
Create a new Excel workbook.
{
"filename": "report",
"outputPath": "/workspace"
}
excel_read_cell
Read a single cell value.
{
"filename": "report.xlsx",
"worksheet": "Sheet1",
"cellAddress": "A1"
}
excel_read_range
Read multiple cells.
{
"filename": "report.xlsx",
"worksheet": "Sheet1",
"startCell": "A1",
"endCell": "C10"
}
excel_write_cell
Write a value to a cell.
{
"filename": "report.xlsx",
"worksheet": "Sheet1",
"cellAddress": "A1",
"value": "Hello World"
}
excel_list_worksheets
List all worksheets in a workbook.
{
"filename": "report.xlsx"
}
excel_add_worksheet
Add a new worksheet.
{
"filename": "report.xlsx",
"worksheetName": "Summary"
}
excel_save_workbook
Save the workbook to disk.
{
"filename": "report.xlsx",
"outputPath": "/workspace/report-final.xlsx"
}
excel_close_workbook
Close an opened workbook.
{
"filename": "report.xlsx"
}
excel_get_cell_info
Get detailed cell information including formulas.
{
"filename": "report.xlsx",
"worksheet": "Sheet1",
"cellAddress": "B5"
}
Security Features
Permission Levels
- read: Read-only access to Excel files
- write: Create and modify Excel files
- delete: Delete worksheets and clear data
- admin: Full administrative access
Path Restrictions
Configure allowed and denied paths using wildcards:
# Allow only specific directories
MCP_ALLOWED_PATHS=/workspace/*,/home/user/documents/*
# Block sensitive system paths
MCP_DENIED_PATHS=/etc/*,/sys/*,/proc/*,C:\Windows\*
File Size Limits
Prevent processing of excessively large files:
MCP_MAX_FILE_SIZE=52428800 # 50MB
Extension Whitelist
Only process specific file types (configured by default):
.xlsx- Excel Workbook.xls- Excel 97-2003 Workbook.xlsm- Excel Macro-Enabled Workbook.xlsb- Excel Binary Workbook
Architecture
excel-mcp/
├── src/
│ ├── index.ts # Application entry point
│ ├── types/
│ │ └── index.ts # Type definitions
│ ├── security/
│ │ └── permission-checker.ts # Access control
│ ├── services/
│ │ └── excel-service.ts # Excel operations
│ ├── tools/
│ │ ├── tool-definitions.ts # Tool schemas
│ │ └── tool-handler.ts # Tool execution
│ ├── server/
│ │ └── excel-mcp-server.ts # MCP server core
│ └── utils/
│ └── logger.ts # Logging utility
├── docs/
│ ├── ARCHITECTURE.md # Architecture details
│ ├── API.md # API reference
│ ├── SECURITY.md # Security guide
│ └── TROUBLESHOOTING.md # Common issues
└── dist/ # Compiled JavaScript
Design Principles
- Single Responsibility: Each class/module has one clear purpose
- Dependency Injection: Components are loosely coupled
- Type Safety: Full TypeScript coverage with strict mode
- Error Handling: Comprehensive error catching and reporting
- Security First: Permission checks before all operations
Development
Scripts
# Development with hot reload
npm run dev
# Build for production
npm run build
# Run tests
npm test
# Lint code
npm run lint
# Format code
npm run format
# Clean build artifacts
npm run clean
Project Structure
src/- TypeScript source filesdist/- Compiled JavaScript outputdocs/- Documentationpackage.json- Dependencies and scriptstsconfig.json- TypeScript configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
MCP_SERVER_NAME |
Server identifier | excel-mcp |
MCP_SERVER_VERSION |
Server version | 1.0.0 |
MCP_LOG_LEVEL |
Logging verbosity | info |
MCP_ALLOWED_PATHS |
Comma-separated allowed paths | All paths |
MCP_DENIED_PATHS |
Comma-separated denied paths | System paths |
MCP_MAX_FILE_SIZE |
Maximum file size in bytes | 52428800 (50MB) |
Troubleshooting
Common Issues
"Permission denied" errors
- Check your
MCP_ALLOWED_PATHSconfiguration - Ensure the file isn't in a denied path
- Verify you have the required permission level
"Workbook not opened" errors
- Call
excel_open_workbookbefore other operations - Check that the file path is correct
- Ensure the file isn't corrupted
TypeScript compilation errors
- Run
npm installto ensure all dependencies are installed - Check Node.js version (requires >= 18.0.0)
For more troubleshooting help, see docs/TROUBLESHOOTING.md.
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please read our contributing guidelines and code of conduct.
Support
- GitHub Issues: Report bugs
- Documentation: Full docs
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.