> 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/authentication-and-authorization.md).

# Authentication and authorization

See how Data Product MCP enforces DataOS identity, access, and policy controls.

MCP defines how clients and servers exchange messages. Authentication and authorization are enforced by the MCP server implementation and the transport configuration used to reach it.

## How Data Product MCP enforces access

Every request is evaluated using the caller's DataOS identity.

If a user cannot access a Data Product, table, column, or value in DataOS, the assistant cannot access it through Data Product MCP. If a value is masked for the user in DataOS, the assistant receives the masked value.

This keeps the assistant inside the same governance boundary as every other DataOS interface.

## How clients authenticate

Data Product MCP accepts two authentication methods, each on its own endpoint:

| Method    | Endpoint                                        | How the client authenticates                                                  |
| --------- | ----------------------------------------------- | ----------------------------------------------------------------------------- |
| OAuth     | `https://<instance-url>/mcp/api/v1`             | The user signs in with their DataOS account in a browser. No token is needed. |
| API token | `https://<instance-url>/dataproduct-mcp/api/v1` | The client sends a DataOS API token in the `apikey` header.                   |

With OAuth, an unauthenticated request returns `401` with a `WWW-Authenticate` header that points to the protected resource metadata at `https://<instance-url>/mcp/api/v1/.well-known/oauth-protected-resource`. Clients that follow the MCP authorization flow use it to find the authorization server and sign the user in. For clients that need the OAuth settings entered manually, see [Custom client](https://v2.dataos.info/consume/consume-with-ai/connect-a-client/custom).

Both methods run each request as the signed-in user or the token owner.

## What the server does on each request

Data Product MCP:

1. Authenticates the caller.
2. Authorizes the requested operation.
3. Applies Data Product policies.
4. Returns only the response the caller is allowed to receive.

The host can improve the conversation around the answer. It does not expand the user's access.


---

# 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/authentication-and-authorization.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.
