# What is MCP? MCP (Model Context Protocol) is a next-generation protocol designed to orchestrate and manage context between users, AI agents, and computational environments across decentralized systems. Unlike traditional compute protocols focused purely on processing, MCP places emphasis on the **context** in which models (such as LLMs) and agents operate. This includes the user prompt history, the task objective, data access scope, verification rules, and the execution environment metadata — all bundled into a trusted, reusable context package. MCP enables: * **Composable agent workflows** where context travels across agents and models * **Secure execution** by binding each task to a verifiable execution context (via zk or TEE) * **Decentralized coordination** of model calls, API access, and storage use * **Modular architecture** for integrating various model providers and runtime tools — The ETMCP Core Team --- # 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.etmcp.com/getting-started/what-is-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.