Excel Bridge MCP server

This MCP Excel server is a Spring AI framework-based project that enables large language models (LLMs) to read and write local Excel files through the MCP protocol. It allows AI to interact with Excel data dynamically, much like a human would use Excel files as a tool.

Features

• Read local Excel files (.xlsx and .xls formats) and return the content as JSON
• Write JSON data to specified local Excel files
• Integration with MCP protocol-supporting LLM clients like Claude, Cursor, and Cherry Studio

System Requirements

• Java 17 or higher

Installation

Building the Application

First, build the package using Maven:

mvn clean package -Dmaven.test.skip=true

Configuring the MCP Server

Set up your MCP server configuration with the following JSON:

{
  "mcpServers": {
    "AUM5itYnoMcxPiU2vFa3Z": {
      "name": "Excel操作",
      "type": "stdio",
      "description": "",
      "isActive": true,
      "command": "java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-Dspring.main.web-application-type=none",
        "-Dfile.encoding=UTF-8",
        "-jar",
        "{your_path}/mcp-excel-server-0.0.1-SNAPSHOT.jar"
      ]
    }
  }
}

Be sure to replace {your_path} with the actual path to your JAR file.

Usage

Once installed and configured, you can use the MCP Excel server to:

1. Read Excel files and get their content as JSON
2. Write JSON data back to Excel files

Working with Excel Files

The server can process both .xlsx and .xls format Excel files. When reading a file, the data will be presented in JSON format, making it easy for the LLM to understand and manipulate the data.

Integration with LLM Clients

The server works with any LLM client that supports the MCP protocol, including:

• Claude
• Cursor
• Cherry Studio

Example Usage

You can use the server to read existing Excel files like order.xlsx and then process the data. The results can be written back to Excel files as needed, creating dynamic interactions between your AI assistant and your Excel data.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.