This project provides a Model Context Protocol (MCP) server designed for AI agents to programmatically create, read, and modify Excel files without requiring a local Microsoft Excel installation. It enables AI agents to interact with Excel data, formatting, charts, and pivot tables, streamlining data analysis and manipulation workflows.

How It Works

The server leverages the Server-Sent Events (SSE) transport protocol to communicate with AI agents. It utilizes Python libraries to handle Excel file operations, allowing for the creation, modification, formatting, charting, and pivot table generation within .xlsx files. This approach abstracts the complexities of direct Excel manipulation, offering a standardized interface for AI tools.

Quick Start & Requirements

• Installation: Clone the repository and install using uv pip install -e ..
• Prerequisites: Python 3.10 or higher.
• Running: Start the server with uv run excel-mcp-server. A custom port can be set via the FASTMCP_PORT environment variable.
• Configuration: For AI tools like Cursor IDE, configure the mcpServers with the SSE endpoint URL and an EXCEL_FILES_PATH.
• Documentation: See TOOLS.md for a complete list of available tools.

Highlighted Details

• Supports creation and modification of Excel workbooks.
• Enables reading and writing of data.
• Allows application of formatting and styles.
• Facilitates creation of charts and visualizations.
• Supports generation of pivot tables.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (like Discord/Slack) is provided in the README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: The MIT license generally permits commercial use and linking with closed-source projects.

Limitations & Caveats

The README does not detail specific limitations, known bugs, or deprecation status. Integration with AI tools like Claude Desktop requires an intermediate step using Supergateway to convert SSE to stdio.