# Model Context Protocol (MCP) At the core of Noctra’s intelligence lies the Model Context Protocol (**MCP**), a cutting-edge framework that optimizes AI models for decentralized environments. MCP is the brain behind Noctra’s agents, enabling them to process real-time on-chain and off-chain data with contextual precision. Its modular architecture supports custom AI models and pre-built templates, making it accessible to developers of all skill levels. By leveraging Aptos’ high-throughput infrastructure, MCP ensures low-latency, scalable computation, allowing agents to make informed decisions in dynamic markets or immersive GameFi scenarios. MCP is the key to unlocking AI’s full potential in the decentralized world. * Data Collection: Tracks user growth, revenue, community feedback, token holding patterns, and risk events. * Dynamic Storage: Stores data on-chain or via secure APIs for real-time access. --- # 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.noctra.ai/model-context-protocol-mcp.md?ask= ``` 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.