Spire.XLS

You can run the Spire.XLS MCP Server to enable AI agents to create, read, edit, and convert Excel workbooks via the Model Context Protocol (MCP). It operates independently from Microsoft Office, delivering high-fidelity Excel manipulation and conversion capabilities through a simple server interface.

How to use

Use an MCP client to connect to the Spire.XLS MCP Server and perform Excel-related actions. You can convert Excel workbooks to formats like PDF, HTML, CSV, images, and XML; read, write, and modify cell data; create charts and pivot tables; manage worksheets and ranges; and build dashboards from your data. Start the server, then configure your MCP client to point at the server URL and provide the path to your Excel files if needed. All operations are exposed through the MCP API as described by the available capabilities.

How to install

# Prerequisites
# Python 3.10 or higher is required

# Step 1: Clone the repository
git clone https://github.com/eiceblue/spire-xls-mcp-server.git
cd spire-xls-mcp-server

# Step 2: Install the MCP server package locally
uv pip install -e .

# Run the MCP server on the default port 8000
uv run spire-xls-mcp-server

# Run the MCP server on a custom port (example: 8080)
# Bash/Linux/macOS
export FASTMCP_PORT=8080 && uv run spire-xls-mcp-server

# Windows PowerShell
$env:FASTMCP_PORT = "8080"; uv run spire-xls-mcp-server

Configuration and environment

Environment variables control server behavior. The following variables are commonly used during operation.

{
  "mcpServers": {
    "excel": {
      "url": "http://localhost:8000/sse",
      "env": {
        "EXCEL_FILES_PATH": "/path/to/excel/files"
      }
    }
  }
}