About Omni Server
Omni Server is a Python MCP server for developers learning the MCP framework. Its modular layout separates prompts, tools, data, and resources, and it is designed to work with Claude Desktop.
Key features
- 01Python MCP server implementation
- 02Modular prompts, tools, and resources
- 03Configuration through .env and Poetry
- 04Claude Desktop integration
Use cases
- 01Explore an MCP server project structure
- 02Learn how MCP applications are organized
- 03Connect the server to Claude Desktop
MCP support
Implements an MCP server with prompts, tools, data, and resources. The README describes configuration for use with Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEOmni Server
Omni Server is a Model Context Protocol (MCP) server designed to help developers familiarize themselves with the MCP framework. It serves as a foundational tool for understanding and implementing MCP-based applications.
Features
- 🚀 MCP server implementation using Python
- 📁 Modular project structure with clear separation of prompts, tools, data, and resources
- ⚙️ Easily configurable with
.envand Poetry - 🧠 Designed to integrate seamlessly with Claude Desktop
Project Structure
omni-server/
├── data/ # Data files and datasets
├── prompts/ # Prompt templates and related files
├── resources/ # Static resources and assets
├── tools/ # Utility scripts and tools
├── utils/ # Helper functions and utilities
├── .env # Environment variable definitions
├── .gitignore # Git ignore rules
├── .python-version # Python version specification
├── README.md # Project documentation
├── main.py # Main application entry point
├── pyproject.toml # Project metadata and dependencies
├── server.py # Server initialization and configuration
└── uv.lock # Dependency lock file
Getting Started
Prerequisites
- Python 3.8 or higher
- uv for dependency management
Installation
- Clone the repository:
git clone https://github.com/abhijithk1/omni-server.git
cd omni-server
- Install dependencies using uv:
uv venv
uv pip install -r requirements.txt # if using requirements.txt
# or, better:
uv pip install -e . # if pyproject.toml is used
- Activate the virtual environment (if needed):
source .venv/bin/activate # macOS/Linux
.venv\Scripts\activate # Windows
- Create a
.envfile (if required) with any necessary environment variables.
Dependencies
All required packages are defined in pyproject.toml. You can install them using:
uv pip install -e .
Running the Server
To run manually via terminal:
uv pip install -e . # ensure it's installed
python main.py
Or if you're using a virtual environment:
.venv/Scripts/python.exe main.py
🧩 Integrating with Claude Desktop
To use this server with Claude Desktop, configure your claude_desktop_config.json like so:
{
"mcpServers": {
"omni_server": {
"command": "<PATH TO PROJECT>/.venv/Scripts/python.exe",
"args": [
"<PATH TO PROJECT>/main.py"
],
"cwd": "<PATH TO PROJECT>"
}
}
}
Make sure:
- The path to the Python executable is correct
- Your virtual environment (.venv) is created and installed via uv
- Claude Desktop is configured to recognize the MCP server
Once that's done, Omni Server will run as an MCP-compatible backend inside Claude Desktop!
Contributing
Contributions are welcome! Fork the repository, make changes, and open a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Comments
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.