> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/references/interfaces/ai-activation/mcp-layers.md).

# MCP layers

Understand the data and transport layers used by Data Product MCP.

MCP separates message meaning from message transport.

## The two layers

| Layer           | What it handles                                                                                                                           | Example                                                                                                                                   |
| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| Data layer      | The JSON-RPC message model, lifecycle, capability negotiation, requests, responses, notifications, errors, tools, resources, and prompts. | The client sends a `tools/call` request with structured arguments for the selected tool. The server returns a structured result or error. |
| Transport layer | The communication channel that carries MCP messages between the client and server.                                                        | A desktop assistant may connect to a local MCP process. A hosted assistant may connect to Data Product MCP over HTTP.                     |

The data layer defines what the client and server are saying. The transport layer defines how those messages move.

## Why this separation matters

This split keeps protocol behavior stable across different connection types.

It also lets Data Product MCP support different host environments without changing tool semantics. A local assistant and a hosted assistant can call the same tools and receive the same response shape, even if they connect differently.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://v2.dataos.info/references/interfaces/ai-activation/mcp-layers.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
