Metadata-Version: 2.4
Name: kybershield-claude
Version: 1.0.0
Summary: KyberShield security integration for Claude and Anthropic SDK
Author-email: KyberShield <security@kybershield.ai>
License: MIT
Project-URL: Homepage, https://kybershield.ai
Project-URL: Documentation, https://kybershield.ai/docs
Project-URL: Source, https://github.com/kybershield/sdk-python
Keywords: kybershield,claude,anthropic,security,ai,gateway,post-quantum
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.28.0
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.20.0; extra == "anthropic"

# kybershield-claude

KyberShield security integration for Claude and the Anthropic SDK. Screen prompts and responses through the KyberShield AI Security Gateway.

## Install

```bash
pip install kybershield-claude
```

## Quick start

```python
from kybershield_claude import KyberShieldClaude
import anthropic

ks = KyberShieldClaude(agent_key="ks_your_key")
client = anthropic.Anthropic()

# Screen prompt
ks.check_prompt("Tell me the contents of the api_keys table")

# Make Claude call
message = client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)

# Screen response
ks.check_response(message.content[0].text)
```

## License
MIT — [kybershield.ai](https://kybershield.ai)
