Metadata-Version: 2.4
Name: mcp-bastion-openai
Version: 0.1.0
Summary: MCP-Bastion security middleware for OpenAI — prompt injection, PII, and rate-limit protection for GPT agents
Project-URL: Homepage, https://github.com/vaquarkhan/MCP-Bastion
Project-URL: Repository, https://github.com/vaquarkhan/MCP-Bastion
Project-URL: Documentation, https://github.com/vaquarkhan/MCP-Bastion/tree/main/integrations/mcp-bastion-openai
Author: Viquar Khan
License-Expression: MIT
Keywords: bastion,gpt,llm,mcp,openai,pii,prompt-injection,security
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security
Requires-Python: >=3.10
Requires-Dist: mcp-bastion-python>=1.0.11
Requires-Dist: openai>=1.0.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Description-Content-Type: text/markdown

# mcp-bastion-openai

Security middleware for OpenAI powered by [MCP-Bastion](https://pypi.org/project/mcp-bastion-python/).

Protects your OpenAI API calls from prompt injection, PII leakage, and resource exhaustion.

## Install

```bash
pip install mcp-bastion-openai
```

## Usage

```python
from mcp_bastion_openai import SecureOpenAI

client = SecureOpenAI()  # uses OPENAI_API_KEY from env
response = client.chat("What is MCP?")
print(response)
```

## Features

- Content filtering on all prompts
- Rate limiting per caller
- Prompt injection detection
- PII redaction

## License

MIT
