What file formats does Excel MCP Server support?
It supports XLSX, XLS, CSV, TSV, and JSON files.
@yzfly
Basic information
The Excel MCP Server is a powerful tool that enables natural language interaction with Excel files through the Model Context Protocol (MCP). It provides a comprehensive set of capabilities for reading, analyzing, visualizing, and writing Excel data.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-excel-server": {
"command": "uv",
"args": [
"init",
"excel-mcp-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An MCP server that provides comprehensive Excel file management and data analysis capabilities. It integrates with the Model Context Protocol and is intended for users who need to read, write, analyze, and visualize Excel data programmatically through AI assistants like Claude Desktop.
Install the server in a Python environment using uv or pip, then integrate it with Claude Desktop by editing the claude_desktop_config.json file to include the uvx mcp-excel-server command. Once configured, you can use the available tools and resources to perform operations on Excel files.
It supports XLSX, XLS, CSV, TSV, and JSON files.
The dependencies are pandas, numpy, matplotlib, and seaborn.
You edit the `claude_desktop_config.json` file to add a server entry with the command `uvx` and arguments `["mcp-excel-server"]`, optionally setting the `PYTHONPATH` environment variable.
Files are read only from specified paths, file size is limited, accidental overwriting is prevented, and data transformation operations are strictly controlled.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Open-source MCP to use Blender with any LLM
Comments