MCP Server for ML Model Integration

Build a MCP Server

A complete walkthrough on how to build a MCP server to serve a trained Random Forest model and integrate it with Bee Framework for ReAct interactivity.

See it live and in action 📺

Startup MCP Server 🚀

1. Clone this repo git clone https://github.com/nicknochnack/BuildMCPServer
2. To run the MCP server
   cd BuildMCPServer
uv venv
source .venv/bin/activate
uv add .
uv add ".[dev]"
uv run mcp dev server.py
3. To run the agent, in a separate terminal, run:
   source .venv/bin/activate
uv run singleflowagent.py

Startup FastAPI Hosted ML Server

git clone https://github.com/nicknochnack/CodeThat-FastML
cd CodeThat-FastML
pip install -r requirements.txt
uvicorn mlapi:app --reload
Detailed instructions on how to build it can also be found here

Other References 🔗

• Building MCP Clients (used in singleflow agent)
• Original Video where I build the ML server

Who, When, Why?

👨🏾‍💻 Author: Nick Renotte 📅 Version: 1.x 📜 License: This project is licensed under the MIT License