Omnillm MCP

🚀 OmniLLM: Universal Bridge for Multilingual Models (Claude Version)

OmniLLM is an MCP server that enables Claude to call and integrate responses from other large language models (LLMs) such as ChatGPT, Azure OpenAI, and Google Gemini. It provides a unified access interface to meet all AI needs.

✨ Features

• Query OpenAI's ChatGPT model.
• Invoke Azure OpenAI services.
• Obtain responses from Google's Gemini.
• Compare the response results of all LLM models.
• View the list of configured and available LLM services.

📦 Installation

1. Prerequisites

• Python 3.10 or higher.
• Claude Desktop application.
• API keys for the required LLM services (e.g., ChatGPT, Azure OpenAI, Google Gemini).

2. Installation Steps

# Clone or download this repository
git clone https://github.com/yourusername/omnillm-mcp.git
cd omnillm-mcp

# Create a virtual environment
python -m venv venv
source venv/bin/activate  # For Windows, use: venv\Scripts\activate

# Install dependencies
pip install mcp[cli] httpx python-dotenv

3. Configuration Steps

Create a .env file in the project root directory and add your API keys:

OPENAI_API_KEY=your_openai_key_here
AZURE_OPENAI_API_KEY=your_azure_key_here
AZURE_OPENAI_ENDPOINT=your_azure_endpoint_here
GOOGLE_API_KEY=your_google_api_key_here

You only need to add the keys corresponding to the LLM services you plan to use.

4. Integration with Claude Desktop

1. Open the Claude Desktop application.
2. Go to Settings > Developer > Edit Configuration.
3. Add server information to the claude_desktop_config.json file:

{
  "mcpServers": {
    "omnillm": {
      "command": "python",
      "args": [
        "path/to/server.py"
      ],
      "env": {
        "PYTHONPATH": "path/to/omnillm-mcp"
      }
    }
  }
}

Replace path/to/server.py with the actual path to your server.py file.

4. Save the configuration file and restart Claude Desktop.

💻 Usage Examples

Once connected to Claude Desktop, you can use statements similar to the following:

• "If I want an adventurous hiking trip, what are the best places to go? Ask ChatGPT for suggestions."
• "What is the best way to learn programming? Get opinions from Gemini."
• "Compare different frameworks for building web applications and get inputs from both ChatGPT and Azure OpenAI."

Claude will automatically recognize when to use the multi-LLM proxy tool to enhance its responses.

📚 Available Functions

1. query_chatgpt - Query OpenAI's ChatGPT with custom prompts.
2. query_azure_chatgpt - Invoke Azure OpenAI's ChatGPT and provide prompts.
3. query_gemini - Obtain responses from Google's Gemini and specify prompts.
4. query_all_llms - Query all available LLM models and return all results.
5. check_available_models - Check which LLM APIs are correctly configured.

🛠️ Troubleshooting

• Ensure that the API keys in the .env file are set correctly.
• Check the paths in the claude_desktop_config.json file.
• If there are connection issues, confirm the network configuration and server status.

📄 Note

For more help or if you encounter other problems, please refer to the project documentation or contact the support team.