Excel MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Excel MCP ServerRead data.xlsx and list all sheet names"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Excel MCP Server
Based on excel-mcp-server by haris-musa – all credit for the core implementation goes to the original author.
Setup
./start_server.shCreates a .venv, installs the package via pip install -e ., and starts the server on port 8002 via streamable HTTP.
Related MCP server: MCP Excel Server
Deployment to Docker host
./deploy_to_remote.sh userSyncs the server via rsync to the Docker host and builds/starts the container via docker compose.
MCP Registration
# Docker / remote
claude mcp add --scope user --transport http excel http://<docker-host>:8002/mcp
# Local
claude mcp add --scope user --transport http excel http://127.0.0.1:8002/mcpFile Transfer
The server runs in Docker and cannot access local file paths (e.g. /Users/…). Files must be uploaded via HTTP before they can be used with MCP tools.
Files are stored in /app/excel_files inside the container (mapped to /mnt/dockershare/excel). All tools expect a relative filename (e.g. data.xlsx) — absolute paths and directory traversal are rejected.
# Upload (required before any tool that takes a filepath)
curl -s -H "X-API-Key: $MCP_API_KEY" -F "file=@data.xlsx" http://<docker-host>:8002/upload
# → returns JSON with "filename": "data.xlsx"
# Download
curl -H "X-API-Key: $MCP_API_KEY" http://<docker-host>:8002/download/data.xlsx -o data.xlsx
# List files
curl -H "X-API-Key: $MCP_API_KEY" http://<docker-host>:8002/files
# Delete single file
curl -X DELETE -H "X-API-Key: $MCP_API_KEY" http://<docker-host>:8002/files/data.xlsx
# Delete all files
curl -X DELETE -H "X-API-Key: $MCP_API_KEY" http://<docker-host>:8002/filesWorkflow for agents
Upload the local file via
curl -s -H "X-API-Key: $MCP_API_KEY" -F "file=@/path/to/file.xlsx" http://<docker-host>:8002/uploadUse the returned
filename(e.g."data.xlsx") asfilepathwith all Excel toolsDo NOT try to read or unzip XLSX files locally — always upload via curl first
API Key
Set MCP_API_KEY in the container environment to require X-API-Key on all /upload, /download, and /files requests. If unset, endpoints are unprotected.
See docker-compose.yml for the placeholder.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.
Browse and manage files in your Moxt AI workspace from any MCP client.
File uploads for AI agents. Upload, list, and manage files. No signup required.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read, write, and manipulate Excel files through comprehensive spreadsheet operations. Supports file management, data querying, worksheet operations, formula calculations, and includes security features like path validation and automatic backups.2MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI agents to automate Excel file operations including workbook creation, worksheet management, and data manipulation. It provides a standardized interface for reading, writing, merging, and filtering cell ranges within Excel documents.4-
- AlicenseAqualityDmaintenanceProvides AI assistants with unified file operations via MCP, supporting Excel, PDF, Word, and SQLite file reading, writing, and querying.12MIT
- AlicenseNot gradedqualityDmaintenanceA 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.MIT