> 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/consume/consume-with-ai/connect-a-client.md).

# Connect a client

Connect an MCP-compatible AI client to Data Product MCP.

Connect an MCP-compatible AI client to Data Product MCP so the assistant can discover, query, and inspect products through DataOS, all within your governance.

## What you need

* Your DataOS instance URL, such as `pacific-051426.dataos.cloud`.
* An AI client that supports MCP over HTTP or streamable HTTP.
* A [DataOS API token](https://v2.dataos.info/references/key-concepts/api-tokens) from [Before you begin](/consume/get-started/before-you-begin.md), if you connect with the API token method.

Every client connects over streamable HTTP, but the endpoint depends on the auth method:

<table><thead><tr><th width="189.840087890625">Method</th><th>Endpoint</th></tr></thead><tbody><tr><td>OAuth</td><td><code>https://&#x3C;instance-url>/mcp/api/v1</code></td></tr><tr><td>API token</td><td><code>https://&#x3C;instance-url>/dataproduct-mcp/api/v1</code></td></tr></tbody></table>

Each client guide covers both, where the client supports it.

## Pick your client

Open **Activate → MCP** from a product, then select your client:

<table><thead><tr><th width="189.840087890625">Client</th><th>For</th></tr></thead><tbody><tr><td><a href="/consume/consume-with-ai/connect-a-client/claude.md">Claude</a></td><td>Claude Code or Claude Desktop, for analysis and development</td></tr><tr><td><a href="/consume/consume-with-ai/connect-a-client/cursor.md">Cursor</a></td><td>Cursor chat and agent workflows</td></tr><tr><td><a href="/consume/consume-with-ai/connect-a-client/copilot-vs-code.md">Copilot in VS Code</a></td><td>GitHub Copilot Chat, with a project-level config</td></tr><tr><td><a href="/consume/consume-with-ai/connect-a-client/codex-desktop.md">ChatGPT Desktop (Codex)</a></td><td>ChatGPT Desktop (Codex) as your MCP assistant</td></tr><tr><td><a href="/consume/consume-with-ai/connect-a-client/custom.md">Custom</a></td><td>Any other MCP-compatible tool, with the generic configuration</td></tr></tbody></table>

## Verify any client

After setup, ask:

```
What data products am I authorized to access?
```

A working connection returns products from your DataOS instance, scoped to your token and permissions. If you get an authentication error instead, ask your administrator for the `mcp-tool-read` grant under the `use-mcp-service` policy use case, or a tenant role such as `data_consumer` or `data_developer`; see [Governance and trust](/consume/consume-with-ai/overview.md#governance-and-trust) for how MCP access is granted. Then move on to [Discover in natural language](/consume/consume-with-ai/discover-in-natural-language.md).


---

# 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/consume/consume-with-ai/connect-a-client.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.