OpenAI MCP Server
# OpenAI MCP Server
Query OpenAI models directly from Claude using MCP protocol.
## Setup
Add to `claude_desktop_config.json`:
```json
{
"mcpServers": {
"openai-server": {
"command": "python",
"args": ["-m", "src.mcp_server_openai.server"],
"env": {
"PYTHONPATH": "C:/path/to/your/mcp-server-openai",
"OPENAI_API_KEY": "your-key-here"
}
}
}
}
```
## Development
```bash
git clone https://github.com/pierrebrunelle/mcp-server-openai
cd mcp-server-openai
pip install -e .
```
## Testing
```python
# Run tests from project root
pytest -v test_openai.py -s
# Sample test output:
Testing OpenAI API call...
OpenAI Response: Hello! I'm doing well, thank you for asking...
PASSED
```
## License
MIT License
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'ask-openai' has a clear and singular purpose, making it impossible for an agent to misselect between tools.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'ask-openai' follows a verb_noun pattern, and with no other tools to compare against, there are no inconsistencies.
A single tool is generally too few for a server's purpose, as it limits functionality and scope. For an 'OpenAI MCP Server', one might expect more comprehensive coverage such as different model interactions, fine-tuning, or other API endpoints, making this feel thin and under-scoped.
The tool set is severely incomplete for an 'OpenAI MCP Server'. With only a direct question tool, it lacks essential operations like model listing, chat completions, embeddings, or file handling, which are core to OpenAI's API. This will likely cause agent failures due to missing functionality.