Choose Your Integration
RAXE integrates with your entire AI stack. Use this guide to find the right integration for your use case.All integrations use the same underlying detection engine with 515+ rules and ML-based classification. Choose the integration that matches your architecture.
Quick Decision Guide
Answer one question to find your integration:I use Claude Desktop, Cursor, or other MCP tools
I use Claude Desktop, Cursor, or other MCP tools
Use: MCP GatewayThe MCP Gateway acts as a transparent security proxy for any Model Context Protocol server. It scans all tool calls and responses without modifying your existing setup.
I'm building with LangChain
I'm building with LangChain
Use: LangChain IntegrationCallback-based scanning for chains, agents, tools, memory, and RAG pipelines. The most comprehensive integration for LangChain applications.
I use multiple LLM providers (OpenAI, Anthropic, Azure, etc.)
I use multiple LLM providers (OpenAI, Anthropic, Azure, etc.)
Use: LiteLLM IntegrationSingle integration for 100+ LLM providers. If you’re using LiteLLM as your abstraction layer, this is the integration for you.
I just use OpenAI directly
I just use OpenAI directly
I just use Anthropic/Claude directly
I just use Anthropic/Claude directly
I'm building multi-agent systems
I'm building multi-agent systems
Choose based on your framework:
| Framework | Integration |
|---|---|
| CrewAI | CrewAI Integration |
| AutoGen | AutoGen Integration |
| LangGraph | LangChain Integration |
| Custom | SDK Direct |
I need enterprise SIEM integration
I need enterprise SIEM integration
Use: SIEM IntegrationStream threat data to Splunk, CrowdStrike, Microsoft Sentinel, ArcSight, or any CEF-compatible SIEM.
I want to scan prompts in CI/CD
I want to scan prompts in CI/CD
Use: CI/CD IntegrationShift-left security scanning with GitHub Actions, pre-commit hooks, or custom pipelines.
Integration Comparison
| Integration | Best For | Effort | Scan Coverage |
|---|---|---|---|
| MCP Gateway | Claude Desktop, Cursor | 5 min | Tool calls, responses |
| LangChain | Agent apps, RAG | 10 min | Prompts, tools, memory, chains |
| LiteLLM | Multi-provider apps | 5 min | All LLM calls |
| OpenAI Wrapper | Simple OpenAI apps | 2 min | Chat completions |
| Anthropic Wrapper | Simple Claude apps | 2 min | Messages API |
| CrewAI | Multi-agent crews | 10 min | Agent messages, tasks |
| AutoGen | Microsoft agents | 10 min | Conversations |
| LlamaIndex | RAG applications | 10 min | Queries, retrievals |
| DSPy | Optimized prompts | 10 min | Module I/O |
| SIEM | Enterprise SOC | 30 min | All detections |
| SDK Direct | Custom integration | Varies | Full control |
Agent Frameworks
Protect multi-agent systems, RAG pipelines, and autonomous AI applications.MCP Gateway
Claude Desktop & Cursor - Transparent security proxy for Model Context Protocol servers.
LangChain
Most Popular - Protect chains, agents, tools, memory, and RAG pipelines with callback-based scanning.
CrewAI
Multi-agent crew protection with task-level scanning and inter-agent message validation.
AutoGen
Microsoft’s multi-agent framework with conversation-level threat detection.
LlamaIndex
RAG-focused protection for document ingestion, retrieval, and query pipelines.
DSPy
Stanford’s declarative language model programming framework with signature-level protection.
Portkey
AI gateway integration for unified observability and security across providers.
OpenClaw
Personal AI Assistant - Protect your self-hosted AI across 13+ messaging channels.
LLM Provider Wrappers
Drop-in replacements for native SDKs with built-in threat detection.LiteLLM
100+ LLM Providers - Single integration for OpenAI, Anthropic, Azure, Bedrock, Vertex AI, and more.
OpenAI
Drop-in replacement for the OpenAI Python SDK. Same API, added security.
Anthropic
Drop-in replacement for the Anthropic Python SDK with Claude protection.
HuggingFace
Protect HuggingFace Transformers and Inference API calls.
Enterprise SIEM
Real-time threat data streaming to your security operations center.Splunk
HTTP Event Collector (HEC) integration for real-time threat indexing.
CrowdStrike
Falcon LogScale (Humio) integration for threat correlation.
Microsoft Sentinel
Azure Data Collector API for cloud-native SIEM integration.
ArcSight
SmartConnector CEF format for enterprise SIEM deployments.
CEF (Generic)
Common Event Format over HTTP, UDP, or TCP/TLS syslog.
QRadar
IBM QRadar via CEF format integration.
Web Frameworks & CI/CD
Protect HTTP endpoints and shift-left security in your deployment pipeline.FastAPI / Flask / Django
Middleware, decorators, and dependency injection patterns for Python web frameworks.
GitHub Actions & Pre-commit
Scan prompts and test data in pull requests. Catch threats before they’re committed.
LLM Providers via LiteLLM
Through our LiteLLM integration, RAXE supports 100+ LLM providers with a single integration:- Cloud Providers
- Open Source
- Specialized
| Provider | Models |
|---|---|
| OpenAI | GPT-4o, GPT-4, GPT-3.5 |
| Anthropic | Claude 3.5, Claude 3, Claude 2 |
| Azure OpenAI | All Azure-hosted models |
| Google Vertex AI | Gemini Pro, PaLM 2 |
| AWS Bedrock | Claude, Llama, Titan |
| Cohere | Command, Embed |
| Mistral AI | Mistral Large, Medium, Small |
What’s Next?
Quick Start
Get protected in 60 seconds
How Detection Works
Understand what RAXE detects and how
