Excel Reader MCP server

The Excel Reader Server is a Model Context Protocol (MCP) implementation that provides tools for reading and parsing Excel (xlsx) files. It makes extracting data from Excel files easy, converting the contents into a structured JSON format that can be used in various applications.

Installation

The server requires Python 3.10 or higher to run. You can install it using pip or uv:

# Using pip
pip install excel-reader-server

# Using uv (recommended)
uv pip install excel-reader-server

Available Tools

The Excel Reader Server provides three different tools for accessing Excel data.

Reading All Sheets

The read_excel tool reads content from all sheets in an Excel file:

{
  "file_path": "path/to/your/excel/file.xlsx"
}

Reading by Sheet Name

Use read_excel_by_sheet_name to read content from a specific sheet by its name:

{
  "file_path": "path/to/your/excel/file.xlsx",
  "sheet_name": "Sheet1"  # optional - reads first sheet if omitted
}

Reading by Sheet Index

Use read_excel_by_sheet_index to read content from a specific sheet by its index:

{
  "file_path": "path/to/your/excel/file.xlsx",
  "sheet_index": 0  # optional - reads first sheet (index 0) if omitted
}

Response Format

The server returns data in a structured JSON format:

{
  "Sheet1": [
    ["Header1", "Header2", "Header3"],
    ["Value1", "Value2", "Value3"],
    ["Value4", "Value5", "Value6"]
  ]
}

Key characteristics of the response:

• Each sheet is represented as a key in the top-level object
• Sheet data is presented as an array of arrays (each inner array is a row)
• All values are converted to strings for consistency
• Empty cells appear as empty strings

Error Handling

The server provides helpful error messages for common issues you might encounter:

• File not found errors
• Invalid sheet name specifications
• Index out of range errors
• General Excel file parsing errors

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.