# PromptGuard

> AI security firewall for LLM applications. Scans every request and response for prompt injection, data leaks, jailbreaks, and PII exposure.

## Documentation

- [Quickstart](https://docs.promptguard.co/quickstart): Add PromptGuard to an existing app in 5 minutes
- [Security Overview](https://docs.promptguard.co/security/overview): What PromptGuard detects and how
- [Threat Detection](https://docs.promptguard.co/security/threat-detection): Detection capabilities and configuration
- [Python SDK](https://docs.promptguard.co/guides/python-sdk): Auto-instrumentation for Python applications
- [Node.js SDK](https://docs.promptguard.co/guides/node-sdk): Auto-instrumentation for Node.js applications
- [CLI](https://docs.promptguard.co/tools/cli): Command-line scanning and redaction
- [MCP Server](https://docs.promptguard.co/tools/mcp): Connect to AI coding editors (Cursor, Claude, VS Code)
- [LLM Providers](https://docs.promptguard.co/guides/llm-providers): OpenAI, Anthropic, Google, Ollama, vLLM, Bedrock
- [Security Policies](https://docs.promptguard.co/security/policy-presets): Presets and custom rules
- [AI Agent Traps](https://docs.promptguard.co/security/ai-agent-traps): Coverage of DeepMind's 21-vector threat framework
- [API Reference](https://docs.promptguard.co/api-reference/introduction): REST API documentation
- [Guard API](https://docs.promptguard.co/api-reference/guard): Standalone content scanning endpoint
- [Rate Limits](https://docs.promptguard.co/production/rate-limits): Request quotas and rate limiting
- [Pricing](https://docs.promptguard.co/pricing): Plans, limits, and feature comparison
- [Compliance](https://docs.promptguard.co/security/compliance): SOC 2, GDPR, infrastructure security

## API Endpoints

- POST /api/v1/guard: Scan messages for threats (input or output direction)
- POST /api/v1/chat/completions: Proxied OpenAI-compatible completions with security scanning
- POST /api/v1/security/scan: Standalone content scanning
- POST /api/v1/security/redact: PII redaction
- GET /api/v1/models: List available models

## Integration

- Python SDK: pip install promptguard-sdk
- Node.js SDK: npm install promptguard-sdk
- CLI: brew install promptguard/tap/promptguard
- HTTP Proxy: Change base URL to https://api.promptguard.co/api/v1

## Links

- Website: https://promptguard.co
- Dashboard: https://app.promptguard.co
- Status: https://status.promptguard.co
- Support: support@promptguard.co