Newaitees Ollama MCP Server

🚀 ollama-MCP-server Project Documentation

ollama-MCP-server is a project based on the Model Context Protocol (MCP). It aims to provide users with a server for running and managing large language models (LLMs) locally. This project utilizes Ollama, a tool for running open - source LLMs locally.

With ollama-MCP-server, users can easily invoke various Ollama - supported models and interact with them via the MCP protocol. The server offers a rich set of features, including but not limited to:

• Model Management: Supports multiple Ollama models.
• API Interfaces: Provides RESTful API and WebSocket interfaces for interaction.
• Scalability: Facilitates integration into larger - scale applications.

✨ Features

Core Features

• Model Execution: Supports running Ollama models locally, such as the LLaMA series and Alpaca.
• API Interfaces: Offers REST - and WebSocket - based APIs for easy integration.
• Context Management: Enables interaction between the model and external systems through the MCP protocol.

Other Features

• Multi - language Support: Supports Chinese and English interfaces and documentation by default.
• Logging System: Comes with a detailed built - in logging function for convenient debugging and monitoring.
• Extension Plugins: Provides a plugin mechanism for easily adding more functional modules.

🚀 Quick Start

Installation

1. Clone the project repository:

   git clone https://github.com/yourusername/ollama-MCP-server.git
   cd ollama-MCP-server
   

2. Create and activate a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows, use: venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

Start the Server

1. Start using the provided script:

   ./run_server.sh
   

2. Add optional parameters:

   --debug  # Enable debug mode (log level: DEBUG)
   --log=LEVEL  # Set the log level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
   

Usage Examples

# Invoke the model via the MCP protocol
response = await mcp.use_mcp_tool({
    "server_name": "ollama-MCP-server",
    "tool_name": "run-model",
    "arguments": {
        "model": "llama3",
        "prompt": "Please briefly explain quantum computing.",
        "temperature": 0.7
    }
})

📦 Installation

System Requirements

• Operating System: Supports Linux, macOS, and Windows.
• Python Version: It is recommended to use Python 3.8 or higher.
• Ollama Installation: Ollama needs to be pre - installed and environment variables configured.

Installation Steps

1. Clone the project repository:

   git clone https://github.com/yourusername/ollama-MCP-server.git
   cd ollama-MCP-server
   

2. Create and activate a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows, use: venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

Configuration

1. Modify the config.py file to set parameters such as the server port and log level.
2. Create a models directory and download the required Ollama model files into it.

💻 Usage Examples

Basic Usage

# Start the server
./run_server.sh

Advanced Features

• Model Management:

  • Supports loading multiple Ollama models.
  • Provides model status monitoring and resource allocation functions.

• Logging and Monitoring

  • Comes with a detailed built - in logging system, supporting multi - level log output.
  • Offers a performance monitoring interface for optimizing server operation.

📚 Documentation

Environment Configuration

1. Clone the project and initialize:

   git clone https://github.com/yourusername/ollama-MCP-server.git
   cd ollama-MCP-server
   

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows, use: venv\Scripts\activate
   

3. Install development dependencies:

   pip install -r requirements.dev.txt
   

Coding Standards

• Follow the PEP8 code style guide.
• Provide detailed comments and documentation for team collaboration.

🤝 Contribution Guide

Submitting Code

1. Create a feature branch:

   git checkout -b feature/your-feature-name
   

2. Commit changes and push to the remote repository:

   git add .
   git commit -m "Describe your changes"
   git push origin feature/your - feature - name
   

📄 License

The specific license information is not provided in the original text. If there is license - related content later, it can be added here.

🙏 Acknowledgments

The specific acknowledgment information is not provided in the original text. If there is acknowledgment - related content later, it can be added here.