About Spire XLS MCP Server
Spire XLS MCP Server lets AI agents create, read, edit, analyze, and convert Excel workbooks without Microsoft Office. It exposes workbook, worksheet, data, chart, pivot table, formatting, and conversion operations.
Key features
- 01Create and edit workbooks
- 02Manage worksheets and cell ranges
- 03Read, write, sort, and filter data
- 04Apply formulas and formatting
- 05Create charts and pivot tables
- 06Convert Excel to multiple formats
Use cases
- 01Edit workbook contents through an AI agent
- 02Analyze and filter spreadsheet data
- 03Build chart-based Excel dashboards
- 04Convert workbooks to PDF, CSV, or HTML
MCP support
Exposes Excel workbook and worksheet operations as tools for MCP clients. Uses SSE transport.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESpire.XLS MCP Server Read Me
What is Spire.XLS MCP Server?
The Spire.XLS MCP Server is a robust solution that empowers AI agents to work with Excel files using the Model Context Protocol (MCP). It is totally independent and doesn't require Microsoft Office to be installed on system. This tool enables AI agents to create, read, modify, and convert Excel workbooks seamlessly
Main Features:
- Convert Excel to PDF, HTML, CSV, image, XML, and more with high fidelity.
- Create, modify, and manage Excel workbooks
- Manage and control worksheets: rename, move, hide, freeze panes, and more.
- Manage worksheets and cell ranges
- Read and write data
- Analyze Excel data
- Add various chart types to create visual Excel dashboards from data
- Create and manipulate pivot tables to summarize, analyze, explore, and present Excel data.
How to use Spire.XLS MCP Server?
Prerequisites
- Python 3.10 or higher
Installation
- Clone the repository:
git clone https://github.com/EiceblueCloud/Spire-XLS-MCP-Server.git
cd spire-xls-mcp-server
- Install using uv:
uv pip install -e .
Running the Server
Start the server (default port 8000):
uv run spire-xls-mcp-server
Custom port (e.g., 8080):
# Bash/Linux/macOS
export FASTMCP_PORT=8080 && uv run spire-xls-mcp-server
# Windows PowerShell
$env:FASTMCP_PORT = "8080"; uv run spire-xls-mcp-server
Integration with AI Tools
Cursor IDE
- Add this configuration to Cursor:
{
"mcpServers": {
"excel": {
"url": "http://localhost:8000/sse",
"env": {
"EXCEL_FILES_PATH": "/path/to/excel/files"
}
}
}
}
- The Excel tools will be available through your AI assistant.
Remote Hosting & Transport Protocols
This server uses Server-Sent Events (SSE) transport protocol. For different use cases:
-
Using with Claude Desktop (requires stdio):
- Use Supergateway to convert SSE to stdio
-
Hosting Your MCP Server:
Environment Variables
| Variable | Description | Default |
|---|---|---|
FASTMCP_PORT | Server port | 8000 |
EXCEL_FILES_PATH | Directory for Excel files | ./excel_files |
Available Tools
The server provides a comprehensive set of Excel manipulation tools. Here are the main categories:
- Basic Operations: Create, read, write, and delete workbooks and worksheets
- Data Processing: Read and write cell data, apply formulas, sort and filter
- Formatting: Apply styles, merge cells, set fonts and colors
- Advanced Features: Create charts, pivot tables, conditional formatting
- Conversion: Convert Excel to PDF, HTML, CSV, image, XML, and more with high fidelity.
See TOOLS.md for complete documentation of all available tools.
FAQ from Spire.XLS MCP Server?
Can I use Spire.XLS MCP Server for any directory? Yes, Spire.XLS MCP Serer works for any directory.
Is Spire.XLS MCP Server free to use? Yes, it is licensed under the MIT License, allowing free use and modification.
What programming languages does Spire.XLS MCP Server support? It is built with Python.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.