Llm Bridge MCP

🚀 LLM Bridge MCP

LLM Bridge MCP enables AI agents to interact with multiple large language models through a unified interface. It uses the Message Control Protocol (MCP) to provide seamless access to different LLM providers, allowing you to easily switch between models or use multiple models simultaneously in your applications.

✨ Features

• Unified interface to access multiple LLM providers:
  • OpenAI (GPT models)
  • Anthropic (Claude models)
  • Google (Gemini models)
  • DeepSeek
  • ...
• Type safety and validation with Pydantic AI
• Support for custom parameters, such as temperature and maximum number of tokens
• Usage tracking and metrics provided

💻 Usage Examples

Basic Usage

The server implements the following tool:

run_llm(
    prompt: str,
    model_name: KnownModelName = "openai:gpt-4o-mini",
    temperature: float = 0.7,
    max_tokens: int = 8192,
    system_prompt: str = "",
) -> LLMResponse

• prompt: The text prompt sent to the LLM.
• model_name: The specific model to use (default: "openai:gpt-4o-mini").
• temperature: Controls randomness (ranging from 0.0 to 1.0).
• max_tokens: The maximum number of tokens to generate.
• system_prompt: An optional system prompt to guide the model's behavior.

📦 Installation

Install using Smithery

Automatically install llm-bridge-mcp via Smithery:

npx -y @smithery/cli install @sjquant/llm-bridge-mcp --client claude

Manual Installation

1. Clone the repository:

git clone https://github.com/yourusername/llm-bridge-mcp.git
cd llm-bridge-mcp

2. Install uv (if not already installed):

# On macOS/Linux
brew install uv

# On Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

📚 Documentation

Configuration

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

OPENAI_API_KEY=your_openai_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
GOOGLE_API_KEY=your_google_api_key
DEEPSEEK_API_KEY=your_deepseek_api_key

Usage with Claude Desktop or Cursor

Add the server entry to your Claude Desktop configuration file or .cursor/mcp.json:

"mcpServers": {
  "llm-bridge": {
    "command": "uvx",
    "args": [
      "llm-bridge-mcp"
    ],
    "env": {
      "OPENAI_API_KEY": "your_openai_api_key",
      "ANTHROPIC_API_KEY": "your_anthropic_api_key"
    }
  }
}