Ollama MCP

🚀 Ollama MCP Server

An MCP (Model Context Protocol) server for Ollama that enables seamless integration of Ollama's local LLM models with MCP-compatible applications, such as Claude Desktop.

✨ Features

• List available Ollama models.
• Pull new Ollama models.
• Chat with models using Ollama's chat API.
• Get detailed model information.
• Automatically manage ports.
• Configure via environment variables.

📦 Installation

Prerequisites

• Node.js (v16 or higher)
• npm
• Installed and running Ollama

Manual Installation

Install globally via npm:

npm install -g @rawveg/ollama-mcp

Installation in Other MCP Applications

To install the Ollama MCP server in other MCP-compatible applications (such as Cline or Claude Desktop), add the following configuration to the application's MCP settings file:

{
  "mcpServers": {
    "@rawveg/ollama-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@rawveg/ollama-mcp"
      ]
    }
  }
}

The location of the settings file varies by application:

• Claude Desktop: claude_desktop_config.json in the Claude application data directory.
• Cline: cline_mcp_settings.json in the VS Code global storage.

💻 Usage Examples

Starting the Server

Simply run:

ollama-mcp

The server will start on port 3456 by default. You can specify a different port via an environment variable:

PORT=3457 ollama-mcp

Environment Variables

• PORT: Server port (default: 3456). Can be used when running directly:

  # When running directly
  PORT=3457 ollama-mcp
  

• OLLAMA_API: Ollama API endpoint (default: http://localhost:11434)

API Endpoints

• GET /models - List available models.
• POST /models/pull - Pull a new model.
• POST /chat - Chat with a model.
• GET /models/:name - Get detailed model information.

🚧 Development

1. Clone the repository:

git clone https://github.com/rawveg/ollama-mcp.git
cd ollama-mcp

2. Install dependencies:

npm install

3. Build the project:

npm run build

4. Start the server:

npm start

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.

However, this does not grant you the right to integrate this project into third - party services or commercial platforms without prior discussion and agreement. Although I previously accepted contributions (such as a Dockerfile and related README updates) to support integration with Smithery, the recent actions of a similar service, Glama, have prompted me to re - evaluate this policy.

Glama chose to incorporate the open - source MCP project into its commercial product without prior notice or consent and then created issue requests asking the maintainers to do unpaid work to ensure compatibility with its platform. This behavior—exploiting community labor for profit without compensation—is not only impolite but also ethically unacceptable.

Therefore, to protect the rights of contributors and the sustainability of the project, I have decided to change the project's license from MIT to AGPL - 3.0 or higher. This change ensures that all companies building commercial products or services that depend on this project must be transparent with the community and share their profits.

Contribution Guidelines

If you wish to contribute to this project, please follow these steps:

1. Submit an Issue: When you encounter a problem or have any questions, feel free to open an issue in the GitHub repository.
2. Fix Bugs: Find a bug or a missing feature that interests you and try to solve it by submitting a Pull Request.
3. Add Features: If you have an idea for a new feature, please discuss it first (via an issue or PR) to ensure it aligns with the overall direction of the project.
4. Improve Documentation: Documentation is an important part of the project, and any suggestions for improvement are welcome.

📄 License

This project is licensed under the AGPL - 3.0.