> 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-agentic-frameworks/custom.md).

# Custom

Connect any agentic framework to Data Product MCP using streamable HTTP.

## Prerequisites

You need:

* Your DataOS instance URL, such as `pacific-051426.dataos.cloud`.
* A DataOS API token generated from [Home → Generate API tokens](/consume/get-started/readme-1.md#get-a-dataos-api-token).
* A framework or SDK that can connect to MCP tools over streamable HTTP.

## Connect the framework

Configure your framework with the values below and replace `<API_TOKEN>` with your token from [API tokens](/consume/get-started/readme-1.md#get-a-dataos-api-token).

| Field        | Value                                           |
| ------------ | ----------------------------------------------- |
| Server name  | `DataProduct-MCP`                               |
| Transport    | Streamable HTTP                                 |
| URL          | `https://<instance-url>/dataproduct-mcp/api/v1` |
| Header key   | `apikey`                                        |
| Header value | `<API_TOKEN>`                                   |

You can also copy these values from **Home → Connect to Data Product MCP** in DataOS. Open the **Data Product MCP config** modal and select **Copy**.

1. Open your framework's MCP client or tool registration settings.
2. Register a new MCP server using the values above.
3. Replace `<API_TOKEN>` with your DataOS API token.
4. Load the available tools from the server and pass them to your agent.

After connecting, your framework can list and call the Data Product MCP tools over HTTP.

## Example configuration

Most MCP client libraries accept a server definition with this shape:

```json
{
  "DataProduct-MCP": {
    "transport": "http",
    "url": "https://<instance-url>/dataproduct-mcp/api/v1",
    "headers": {
      "apikey": "<API_TOKEN>"
    }
  }
}
```

Adapt the syntax to your framework's MCP adapter. See [LangChain](/consume/consume-with-ai/connect-agentic-frameworks/langchain.md) or [Vercel AI SDK](/consume/consume-with-ai/connect-agentic-frameworks/vercel-ai-sdk.md) for framework-specific examples.

## Verify the connection

After registration, list the available tools from `DataProduct-MCP`. You should see the Data Product MCP tool surface exposed by your DataOS instance.

Then ask your agent:

```
What Data Products am I authorized to access?
```

If the connection works, the agent returns Data Products scoped to your token and permissions.

## Next steps

* [LangChain](/consume/consume-with-ai/connect-agentic-frameworks/langchain.md) - See a framework-specific connection example.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://v2.dataos.info/consume/consume-with-ai/connect-agentic-frameworks/custom.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.