# AI Agent + Model Context Protocol (MCP)

OcularAI’s AI agent serves as the primary interface for executing on-chain actions through natural voice and gesture input. It is built on a hybrid processing model: lightweight on-device inference handles real-time command recognition and environment sensing, while high-order language understanding is delegated to a mobile-hosted or edge-inferred large language model.

At the center of this system is the Model Context Protocol (MCP)—a real-time framework that constructs a structured execution context from live user data. This includes parameters like geolocation, device posture, wallet balances, current dApp activity, and even nearby visual inputs. MCP packages this information into a serialized and cryptographically signed payload, which then conditions the AI model’s response for maximum contextual relevance and security.

This architecture allows OcularAI to support modular agent behaviors—for example, swapping between DeFi execution, NFT handling, or governance voting based on user context—without compromising privacy or responsiveness. By decoupling perception from cognition and enforcing deterministic context formatting, MCP transforms OcularAI’s AI agent into a secure, autonomous execution layer tailored for dynamic interaction within the decentralized web.

<br>


---

# 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://docs.ocularai.xyz/under-the-hood-ocularais-infrastructure/ai-agent-+-model-context-protocol-mcp.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.