MCP OpenAI Tools

A Model Context Protocol (MCP) server that provides access to OpenAI's advanced models (including o3) with web search, code interpreter, and combined analysis capabilities.

Features

Web Search: Search the web using OpenAI's integrated web search capability
Code Interpreter: Execute Python code in OpenAI's sandboxed environment
Search & Analyze: Combine web search with code analysis in a single operation
Direct Prompting: Send prompts directly to OpenAI models with optional web search
Health Check: Monitor server status and configuration
Configurable Reasoning: Adjust reasoning effort levels (low, medium, high) for optimal performance

Prerequisites

Python 3.11 or higher
OpenAI API key with access to o3 or other supported models
uv package manager (recommended) or pip

Installation

Option 1: Install from Source (Recommended for Development)

Clone the repository:

git clone https://github.com/evandavid1/mcp-openai-tools.git
cd mcp-openai-tools

Create a virtual environment and install dependencies:

# Using uv (recommended)
uv venv
uv pip install -e .

# Or using pip
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

Option 2: Install as a Dependency in Your Project

# Using uv
uv add /path/to/mcp-openai-tools

# Or using pip
pip install /path/to/mcp-openai-tools

Configuration

1. Set up your API Key

Create a .env file in your project root (not in the mcp-openai-tools directory):

OPENAI_API_KEY=your-api-key-here
OPENAI_MODEL=o3  # Optional, defaults to gpt-5

Security Note: Never commit your .env file to version control. Add it to your .gitignore.

2. Configure MCP Server

Add the mcp-openai-tools server to your .mcp.json configuration:

For Local Development:

{
  "mcpServers": {
    "mcp-openai-tools": {
      "type": "stdio",
      "command": "/path/to/mcp-openai-tools/.venv/bin/python",
      "args": ["-m", "mcp_openai_tools.main"],
      "cwd": "/path/to/your/project",
      "env": {
        "OPENAI_MODEL": "o3"
      }
    }
  }
}

For Installed Package:

{
  "mcpServers": {
    "mcp-openai-tools": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "mcp_openai_tools.main"],
      "cwd": "/path/to/your/project",
      "env": {
        "PYTHONPATH": "/path/to/mcp-openai-tools/src",
        "OPENAI_MODEL": "o3"
      }
    }
  }
}

3. Environment Variable Options

The server supports multiple ways to specify the .env file location:

Default: Looks for .env in the current working directory
Parent Directories: Searches up to 3 parent directories

Custom Path: Set ENV_FILE environment variable to specify a custom path:

"env": {
  "ENV_FILE": "/custom/path/to/.env",
  "OPENAI_MODEL": "o3"
}

Usage

Available Tools

Once configured, the following tools are available in your MCP client (e.g., Claude Code):

openai_web_search: Search the web for current information

Parameters:
- query: Search query string
- reasoning_effort: "low" | "medium" | "high" (default: "medium")
- model: Optional model override

openai_code_interpreter: Execute Python code in a sandboxed environment

Parameters:
- instruction: What to do with the code
- code: Optional Python code (generated if not provided)
- reasoning_effort: "low" | "medium" | "high" (default: "medium")
- model: Optional model override

openai_search_and_analyze: Combine web search with code analysis

Parameters:
- task: Description of what to search and analyze
- reasoning_effort: "low" | "medium" | "high" (default: "medium")
- model: Optional model override

openai_prompt: Direct prompting with optional web search

Parameters:
- text: Prompt text
- reasoning_effort: "low" | "medium" | "high" (default: "medium")
- model: Optional model override
- include_web_search: Enable web search (default: true)

openai_health_check: Check server status and configuration
```
Parameters: None
```

Example Usage in Claude Code

# Web search example
result = openai_web_search(
    query="latest developments in quantum computing 2024",
    reasoning_effort="high"
)

# Code interpreter example
result = openai_code_interpreter(
    instruction="Create a visualization of fibonacci sequence growth",
    code="import matplotlib.pyplot as plt\n# Generate fibonacci...",
    reasoning_effort="medium"
)

# Combined search and analysis
result = openai_search_and_analyze(
    task="Find current S&P 500 data and create a performance chart",
    reasoning_effort="high"
)

Troubleshooting

Common Issues

"OPENAI_API_KEY environment variable is not set"
- Ensure your .env file exists and contains OPENAI_API_KEY=your-key
- Check that the working directory (cwd) in .mcp.json points to your project directory
- Try setting ENV_FILE environment variable to the absolute path of your .env file
"No .env file found. Using system environment variables only"
- This warning appears when no .env file is found but may still work if you've set environment variables in your system
- Check the server logs to see which directories were searched
Module not found errors
- Ensure PYTHONPATH is set correctly in .mcp.json if using the package from another location
- Verify the virtual environment is activated if running locally
API errors or model access issues
- Verify your API key has access to the specified model (o3, gpt-5, etc.)
- Check OpenAI API status and your account limits

Debugging

Enable detailed logging by checking the server output. The server logs:

Where it's looking for .env files
Which .env file was loaded (if any)
API configuration status
Tool execution details

Development

Running Tests

# Using pytest
pytest tests/

# With coverage
pytest tests/ --cov=mcp_openai_tools

Project Structure

mcp-openai-tools/
 src/
    mcp_openai_tools/
        __init__.py
        main.py           # Entry point
        server.py         # MCP server setup
        core/            
           config.py     # Configuration management
           client.py     # OpenAI client setup
        tools/           
           web_search.py
           code_interpreter.py
           search_analyze.py
           prompt.py
           health_check.py
        prompts/         
            user_prompts.py
 tests/
 .env.example              # Example environment file
 .mcp.json.example         # MCP configuration example
 pyproject.toml           # Package configuration
 README.md                # This file

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Make your changes with tests
Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues, questions, or suggestions:

Open an issue on GitHub
Check existing issues for solutions
Review the server logs for debugging information

服务配置

[{'mcpServers': {'mcp-openai-tools': {'args': ['-m', 'mcp_openai_tools.main'], 'command': '/path/to/mcp-openai-tools/.venv/bin/python', 'cwd': '/path/to/your/project', 'env': {'OPENAI_MODEL': 'o3'}, 'type': 'stdio'}}}, {'mcpServers': {'mcp-openai-tools': {'args': ['-m', 'mcp_openai_tools.main'], 'command': 'python', 'cwd': '/path/to/your/project', 'env': {'OPENAI_MODEL': 'o3', 'PYTHONPATH': '/path/to/mcp-openai-tools/src'}, 'type': 'stdio'}}}]

来源

来源：github
链接：https://github.com/evandavid1/mcp-openai-tools