# Protocol Support in Akto

Akto provides comprehensive support for modern agentic architectures and AI agent communication protocols, ensuring you can discover, probe, and secure your entire agentic ecosystem regardless of the protocol or framework. Our platform seamlessly handles:

## Supported Protocols

### Model Context Protocol (MCP)

Complete support for the Model Context Protocol including:

* MCP server discovery and tool enumeration
* MCP resource access monitoring
* MCP prompt template analysis
* Security probing for MCP endpoints

### RESTful APIs

Full support for REST-based agent endpoints including:

* All standard HTTP methods (GET, POST, PUT, DELETE, PATCH)
* Agent HTTP endpoints and webhooks
* RESTful tool invocations
* API-based agent integrations

### GraphQL

Complete probing capabilities for GraphQL-based agentic systems:

* GraphQL queries and mutations for agent operations
* Schema introspection for agent capabilities
* GraphQL subscriptions for real-time agent updates

### gRPC

Probing for high-performance RPC frameworks commonly used in agentic systems:

* gRPC service definitions for agents
* Streaming agent communications
* Binary protocol support for efficient agent-to-agent communication

### WebSocket

Real-time bidirectional communication for interactive agents:

* WebSocket connections for streaming agent responses
* Real-time agent state updates
* Persistent agent session monitoring

### SOAP/XML

Support for legacy and enterprise agent integrations:

* Traditional SOAP web services
* XML-based agent communication
* Enterprise service bus integrations

## Framework Support

Akto automatically detects and supports popular agentic frameworks:

* **LangChain**: Full support for LangChain agent protocols
* **LlamaIndex**: Complete coverage for LlamaIndex query engines
* **CrewAI**: Multi-agent orchestration protocol support
* **AutoGen**: Microsoft AutoGen agent communication
* **OpenAI Assistants**: OpenAI Assistant API protocol
* **Anthropic Claude**: Claude API and function calling
* **Custom Agents**: Generic HTTP/JSON agent protocols

## Communication Patterns

Akto monitors and secures various agentic communication patterns:

* **Request-Response**: Traditional synchronous agent invocations
* **Streaming**: Real-time streaming responses from LLMs
* **Tool Calling**: Agent tool invocation and execution
* **Multi-Agent**: Agent-to-agent communication and orchestration
* **Callback**: Webhook-based agent notifications
* **Event-Driven**: Asynchronous agent event processing

Whether you're building modern AI agents with cutting-edge frameworks or maintaining legacy integrations, Akto ensures comprehensive security coverage across all your agentic communications.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery/concepts/protocol-support-in-akto.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.