excel-mcp-server

About excel-mcp-server

A Model Context Protocol (MCP) server that lets you manipulate Excel files without needing Microsoft Excel installed. Create, read, and modify Excel workbooks with your AI agent.

When running the server with the SSE or Streamable HTTP protocols, you must set the EXCEL_FILES_PATH environment variable on the server side. This variable tells the server where to read and write Excel files. - If not set, it defaults to ./excel_files. - With these transports, tool filepath values must be relative to that directory (e.g. reports/q1.xlsx); absolute paths and directory traversal are rejected.

You can also set the FASTMCP_PORT environment variable to control the port the server listens on (default is 8017 if not set). - Example (Windows PowerShell):

From the project's README

excel-mcp-server is an open-source project written primarily in Python, with 4.2k stars on GitHub. It was last updated in September 2026.

Add excel-mcp-server to your MCP client

Generated from the launch command in the project's README. Your client starts the server on demand.

claude mcp add excel-mcp-server -- uvx excel-mcp-server stdio

{
  "mcpServers": {
    "excel-mcp-server": {
      "command": "uvx",
      "args": ["excel-mcp-server", "stdio"]
    }
  }
}

{
  "servers": {
    "excel-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": ["excel-mcp-server", "stdio"]
    }
  }
}

{
  "mcpServers": {
    "excel-mcp-server": {
      "command": "uvx",
      "args": ["excel-mcp-server", "stdio"]
    }
  }
}

[mcp_servers.excel-mcp-server]
command = "uvx"
args = ["excel-mcp-server", "stdio"]

Check the project's README for required accounts, keys and permissions before connecting. Setup guide for each client →