excel-mcp-server
Author: haris-musa
Description: Model Context Protocol server that lets AI agents create, read and modify Excel workbooks without a local Excel install.
Stars: 1.8k
Forks: 206
License: MIT License
Category: Open Source
Overview
Installation
1. Prerequisites
• Python 3.9 or newer
• (optional) A virtual-environment tool such as venv or Conda
2. Install from PyPI (recommended)
pip install excel-mcp-server OR install the bleeding edge version from source:
git clone https://github.com/haris-musa/excel-mcp-server.git
cd excel-mcp-server
pip install -e .3. Environment variables (minimum)
# token used by the MCP server when it has to call an upstream LLM provider
export OPENAI_API_KEY="<your-openai-key>"
# port the HTTP/SSE service will bind to
export MCP_PORT=80804. Launch the server
python -m excel_mcp_server
# or, if a CLI entry-point is provided
excel-mcp-server --host 0.0.0.0 --port ${MCP_PORT}5. Verify
Open http://localhost:8080/health in a browser or run
curl http://localhost:8080/health A JSON payload such as `{"status":"ok"}` means the service is up.
License: MIT License
Updated 7/30/2025