mcpField
🚀
🚀 FastMCP Boilerplate

🚀 FastMCP Boilerplate

Local
github.com/rainer85ahDeveloper Tools15Updated 32w ago
Repository

About 🚀 FastMCP Boilerplate

FastMCP Boilerplate is a Python-based MCP server template built with FastAPI and Docker, integrating Ollama and Open-webUI. It is intended for developers building AI chat platforms, model-routing gateways, or ML backends, with a pluggable structure and REST API documentation.

Key features

  1. 01Docker-based startup
  2. 02Ollama and Open-webUI integration
  3. 03Pluggable models and routes
  4. 04REST API and OpenAPI documentation

Use cases

  1. 01Building AI chat platforms
  2. 02Creating model-routing gateways
  3. 03Setting up LLM development sandboxes
  4. 04Developing FastAPI-based ML backends

MCP support

The project provides an MCP server at `/service/mcp/` for MCP clients to connect to.

#mcp-server#fastmcp#docker

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "rainer85ah": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "compose"
      ]
    }
  }
}
Run commanddocker run -i --rm compose

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocicompose

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

License: MIT Python Docker

🚀 FastMCP Boilerplate for MCP Servers

A modern MCP (Model Control Protocol) project built with Python, FastMCP, FastAPI, Docker, and integrated with Ollama and Open-webUI.

This project provides a lightweight, extensible foundation for building and deploying intelligent systems that manage and expose AI/LLM capabilities.

Model Control Protocol (MCP)

🔧 Tech Stack

  • 🐍 Python – Primary language
  • ⚡ FastMCP – Model Control Protocol framework for managing AI models
  • 🌐 FastAPI – High-performance API backend
  • 🧠 Ollama – LLM execution and orchestration
  • 🧩 Open-webUI – Chat-style interface for AI interactions
  • 🐳 Docker – Containerized for easy deployment and reproducibility in dev and production environments.

🧱 Features

  • 🚀 Fast startup with Docker
  • 🔌 Easy integration with Ollama and Open-webUI
  • 📦 Pluggable architecture for adding models and routes
  • 🎯 Designed for rapid prototyping or production use
  • ✅ REST API ready with OpenAPI docs

📦 Getting Started

1. Clone the repo

git clone https://github.com/rainer85ah/mcp-server.git
cd mcp-server
🐳 2. Run with Docker Compose (recommended)

docker compose up --build -d
3. Access the app

Ollama: http://localhost:11434
API Docs: http://localhost:8000/docs
OpenAPI: http://localhost:8000/openapi.json
MCP Server: http://localhost:8000/service/mcp/
Open-webUI: http://localhost:3000

🌱 Use as a Boilerplate

Use this project as a starter template for:

  • AI chat platforms
  • Model routing gateways
  • Developer LLM sandboxes
  • FastAPI-based ML backends

📜 License

This project is licensed under the MIT License.
You are free to use, modify, and distribute this software with proper attribution.

🤝 Contributing

Contributions are welcome! Feel free to:

  • ⭐ Star the project
  • 🍴 Fork the repo
  • 🛠️ Open issues or feature requests
  • 🔁 Submit pull requests

📫 Contact

Created with 💡 by Rainer Arencibia
🔗 Connect with me on LinkedIn

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.