mcp-registry/excel-mcp-server


    ==================
      
       /// MCP ///
      /// EXC ///
        
    ==================
        
    [server:online]
    [protocol:ready]

excel-mcp-server

by haris-musa

Model Context Protocol server that lets AI agents create, read and modify Excel workbooks without a local Excel install.

1.8k

206

Open Source

GitHub Website Documentation

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=8080

4. 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.

Documentation

License: MIT License

Updated 7/30/2025

excel-mcp-server

Installation

Documentation

Table of Contents