mcpField
E
Excel MCP Server 🚀

Excel MCP Server 🚀

Local
github.com/vijjeswarapusuryatejaProductivity1Updated 79w ago
Repository

About Excel MCP Server 🚀

A lightweight MCP server for automating Excel through natural-language requests, with GPT-4o translating requests into tool calls. It pairs a FastAPI backend with a Streamlit interface.

Key features

  1. 01Excel operations exposed as MCP tools
  2. 02GPT-4o prompt orchestration
  3. 03Multi-tool call execution
  4. 04Streamlit chat interface

Use cases

  1. 01Creating sheets and writing cells from requests
  2. 02Automating Excel edits through chat

MCP support

The FastAPI backend exposes Excel operations as MCP tools for clients. GPT-4o coordinates natural-language requests into structured tool calls.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Excel MCP Server 🚀

This project implements a lightweight Model Context Protocol (MCP) server for Excel automation, powered by OpenAI's ChatGPT (GPT-4o).

You can create, edit, and automate Excel files through natural language prompts, with GPT translating your intent into structured tool calls.

✨ Features

  • Lightweight FastAPI backend exposing Excel operations as MCP tools
  • Natural language prompt handling with GPT-4o orchestration
  • Multi-tool call execution (supports workflows like creating sheets + writing cells)
  • Streamlit frontend to interact easily
  • Minimal setup — no complex SDKs required

📦 Project Structure

FilePurpose
excel_mcp_server.pyFastAPI backend with Excel MCP tools and GPT integration
frontend.pyStreamlit frontend for chatting with Excel
requirements.txt(Coming soon) List of Python dependencies

🚀 How to Run Locally

  1. Clone this repo:
git clone https://github.com/vijjeswarapusuryateja/excel_mcp_server.git
cd excel_mcp_server
  1. Create a virtual environment:
python3 -m venv venv
source venv/bin/activate  # Mac/Linux
venv\Scripts\activate  # Windows
  1. Install required packages:
pip install -r requirements.txt
  1. Run the backend server:
python excel_mcp_server.py
  1. In a new terminal, run the frontend:
streamlit run frontend.py

📚 Related Article

I wrote a full Medium article explaining the architecture, how I built this project, and what I learned about MCP:

👉 Read the article here

🧐 Future Improvements

  • Dockerize backend + frontend
  • Add batch writing tools
  • Add style formatting (bold, colors)
  • Support uploading/downloading Excel files through API

📜 License

MIT License

🌟 If you found this project useful, give it a ⭐ star and feel free to fork/extend!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.