openai mcp

# OpenAI MCP Server

This project implements a FastMCP server that provides a bridge between Claude and OpenAI's API, allowing Claude to interact with various OpenAI models.

## Overview

The server exposes two main tools:
1. `get_openai_models()`: Retrieves a list of all available OpenAI models
2. `ask_openai_model()`: Sends prompts to specified OpenAI models and returns their responses

## Prerequisites

- Python environment
- OpenAI API key (set as environment variable `OPENAI_API_KEY`)
- FastMCP package
- OpenAI Python client

## Setup

1. Clone this repository
2. Install dependencies:
   ```bash
   pip install fastmcp openai
   ```
3. Set your OpenAI API key as an environment variable:
   ```bash
   export OPENAI_API_KEY='your-api-key-here'
   ```

## Usage

Run the server:
```bash
python openai_api.py
```

The server will start and expose the following tools:

### get_openai_models()
Returns a list of all available OpenAI models and their configurations.

### ask_openai_model(model, system_prompt, prompt)
Sends a prompt to a specified OpenAI model and returns its response.

Parameters:
- `model`: The OpenAI model to use (e.g., "gpt-3.5-turbo")
- `system_prompt`: The system message that sets the context for the model
- `prompt`: The user's question or input

## Example

```python
# Get available models
models = get_openai_models()

# Ask a question
response = ask_openai_model(
    model="gpt-3.5-turbo",
    system_prompt="You are a helpful assistant.",
    prompt="What is the capital of France?"
)
```

## Security Note

Make sure to keep your OpenAI API key secure and never commit it to version control. Always use environment variables or secure secret management systems to handle API keys.