Excel Reader Server
The Excel Reader Server is a MCP server that provides tools for reading and extracting data from Excel (xlsx) files in JSON format.
Capabilities include:
Reading content from all sheets in an Excel file
Extracting data from a specific sheet by name (defaults to first sheet if unspecified)
Extracting data from a specific sheet by index (defaults to index 0 if unspecified)
Returning data structured as arrays of arrays (representing rows and cells)
Converting all values to strings and representing empty cells as empty strings
Providing clear error handling for common issues like file not found, invalid sheet names, or index out of range
Provides tools for reading and parsing Excel (.xlsx) files using Python, enabling extraction of data from entire workbooks or specific sheets by name or index.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Excel Reader Server read the sales data from Q1_report.xlsx"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Excel Reader Server
A Model Context Protocol (MCP) server that provides tools for reading Excel (xlsx) files.
Features
Read content from all sheets in an Excel file
Read content from a specific sheet by name
Read content from a specific sheet by index
Returns data in JSON format
Handles empty cells and data type conversions
Related MCP server: OpenPyXL MCP Server
Installation
Requires Python 3.10 or higher.
# Using pip
pip install excel-reader-server
# Using uv (recommended)
uv pip install excel-reader-serverDependencies
mcp >= 1.2.1
openpyxl >= 3.1.5
Usage
The server provides three main tools:
1. read_excel
Reads content from all sheets in an Excel file.
{
"file_path": "path/to/your/excel/file.xlsx"
}2. read_excel_by_sheet_name
Reads content from a specific sheet by name. If no sheet name is provided, reads the first sheet.
{
"file_path": "path/to/your/excel/file.xlsx",
"sheet_name": "Sheet1" # optional
}3. read_excel_by_sheet_index
Reads content from a specific sheet by index. If no index is provided, reads the first sheet (index 0).
{
"file_path": "path/to/your/excel/file.xlsx",
"sheet_index": 0 # optional
}Response Format
The server returns data in the following JSON format:
{
"Sheet1": [
["Header1", "Header2", "Header3"],
["Value1", "Value2", "Value3"],
["Value4", "Value5", "Value6"]
]
}Each sheet is represented as a key in the top-level object
Sheet data is an array of arrays, where each inner array represents a row
All values are converted to strings
Empty cells are represented as empty strings
Error Handling
The server provides clear error messages for common issues:
File not found
Invalid sheet name
Index out of range
General Excel file reading errors
License
This project is released under the Apache 2 License. See the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Available Tools
3 toolsread_excelC
Read content from Excel (xlsx) files
Inputs: file_path (required).
read_excel_by_sheet_indexA
Read content from a specific sheet by index in Excel (xlsx) files. Reads first sheet (index 0) if sheet_index not provided.
Inputs: file_path (required), sheet_index.
read_excel_by_sheet_nameA
Read content from a specific sheet by name in Excel (xlsx) files. Reads first sheet if sheet_name not provided.
Inputs: file_path (required), sheet_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The tools have significant overlap in purpose, as all three are focused on reading Excel files, with only minor variations in how they specify the sheet. An agent might easily confuse them or struggle to choose the right one for a given task, since the distinctions are subtle and not clearly differentiated in the descriptions.
The tool names follow a consistent verb_noun pattern with 'read_excel' as the base, and suffixes like '_by_sheet_index' and '_by_sheet_name' that clearly indicate the specific functionality. This makes the naming predictable and easy to understand across the set.
With only 3 tools, the server feels thin for a domain like Excel reading, which might benefit from additional operations such as writing, listing sheets, or handling different file formats. However, the count is not extreme and could be considered borderline for basic functionality.
The tool set is severely incomplete for an Excel server, as it only covers reading operations and lacks any writing, updating, or other common Excel functionalities like formatting, formula evaluation, or metadata access. This will likely cause agent failures when more comprehensive tasks are required.
Maintenance
Related MCP Connectors
The Excel engine for AI agents: read, check and edit Excel models over MCP.
Hosted MCP: CSV/XLSX to JSON rows and text-PDF pages; private uploads or URLs, no API key.
Token-free MCP server for structured RevoGrid Core, Pro, and Enterprise knowledge retrieval.
Read-only MCP over your Excel or Airtable plus the PDFs beside it, joined as one relational dataset.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to read from and write to Microsoft Excel files, supporting formats like xlsx, xlsm, xltx, and xltm.61,051MIT
- AlicenseAqualityBmaintenanceA thin wrapper around the OpenPyXl Python library that exposes Excel file operations as a Model Context Protocol (MCP) server, allowing Claude and other MCP clients to fetch and analyze data from Excel files.619MIT
- AlicenseAqualityDmaintenanceMCP server for reading and writing Excel (xlsx) files using SheetJS, providing tools to list sheets, read data, create files, add sheets, and update cells.510 npmMIT
- AlicenseAqualityCmaintenanceMCP server for reading and inspecting local Excel files (.xlsx, .xlsm, .xls, .xlsb, .ods) with tools for inspecting metadata, reading ranges, and profiling structure.36 npmMIT