excel_mcp_server
1
The Excel MCP Server is designed to automate Excel tasks through natural language inputs, leveraging the power of GPT-4o. It features a FastAPI backend for handling Excel operations and a Streamlit frontend for user interaction, aiming to simplify Excel automation without complex setup requirements.
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
| File | Purpose |
|---|---|
excel_mcp_server.py | FastAPI backend with Excel MCP tools and GPT integration |
frontend.py | Streamlit frontend for chatting with Excel |
requirements.txt | (Coming soon) List of Python dependencies |
🚀 How to Run Locally
- Clone this repo:
git clone https://github.com/vijjeswarapusuryateja/excel_mcp_server.git
cd excel_mcp_server
- Create a virtual environment:
python3 -m venv venv
source venv/bin/activate # Mac/Linux
venv\Scripts\activate # Windows
- Install required packages:
pip install -r requirements.txt
- Run the backend server:
python excel_mcp_server.py
- 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:
🧐 Future Improvements
- Dockerize backend + frontend
- Add batch writing tools
- Add style formatting (bold, colors)
- Support uploading/downloading Excel files through API
📜 License
MIT License